diff --git "a/less60wer.ipynb" "b/less60wer.ipynb"
new file mode 100644--- /dev/null
+++ "b/less60wer.ipynb"
@@ -0,0 +1,11400 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "LBSYoWbi-45k"
+   },
+   "source": [
+    "# **Fine-tuning XLSR-Wav2Vec2 for Multi-Lingual ASR with 🤗 Transformers**"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### based on the turkish example\n",
+    "\n",
+    "Locally my dataset is `nahuatl_slr90_by_sentence` but it should be `nahuatl_slr92_by_sentence`.\n",
+    "\n",
+    "There are some **nahuatl notes**, also I filtered samples between 1 and 3 seconds to not fall in some problems of resampling or normalization of loudness, but at end did skip normalization because some samples sounded weird (not all).\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "V7YOT2mnUiea"
+   },
+   "source": [
+    "Wav2Vec2 is a pretrained model for Automatic Speech Recognition (ASR) and was released in [September 2020](https://ai.facebook.com/blog/wav2vec-20-learning-the-structure-of-speech-from-raw-audio/) by Alexei Baevski, Michael Auli, and Alex Conneau.  Soon after the superior performance of Wav2Vec2 was demonstrated on the English ASR dataset LibriSpeech, *Facebook AI* presented XLSR-Wav2Vec2 (click [here](https://arxiv.org/abs/2006.13979)). XLSR stands for *cross-lingual  speech representations* and refers to XLSR-Wav2Vec2`s ability to learn speech representations that are useful across multiple languages.\n",
+    "\n",
+    "Similar to Wav2Vec2, XLSR-Wav2Vec2 learns powerful speech representations from hundreds of thousands of hours of speech in more than 50 languages of unlabeled speech. Similar, to [BERT's masked language modeling](http://jalammar.github.io/illustrated-bert/), the model learns contextualized speech representations by randomly masking feature vectors before passing them to a transformer network.\n",
+    "\n",
+    "![wav2vec2_structure](https://raw.githubusercontent.com/patrickvonplaten/scientific_images/master/xlsr_wav2vec2.png)\n",
+    "\n",
+    "The authors show for the first time that massively pretraining an ASR model on cross-lingual unlabeled speech data, followed by language-specific fine-tuning on very little labeled data achieves state-of-the-art results. See Table 1-5 of the official [paper](https://arxiv.org/pdf/2006.13979.pdf)."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "nT_QrfWtsxIz"
+   },
+   "source": [
+    "In this notebook, we will give an in-detail explanation of how XLSR-Wav2Vec2's pretrained checkpoint can be fine-tuned on a low-resource ASR dataset of any language. Note that in this notebook, we will fine-tune XLSR-Wav2Vec2 without making use of a language model. It is much simpler and more efficient to use XLSR-Wav2Vec2 without a language model, but better results can be achieved by including a language model. \n",
+    "\n",
+    "For demonstration purposes, we fine-tune the [wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the low resource Turkish ASR dataset of [Common Voice](https://huggingface.co/datasets/common_voice) that contains just ~6h of validated training data."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "Gx9OdDYrCtQ1"
+   },
+   "source": [
+    "XLSR-Wav2Vec2 is fine-tuned using Connectionist Temporal Classification (CTC), which is an algorithm that is used to train neural networks for sequence-to-sequence problems and mainly in Automatic Speech Recognition and handwriting recognition. \n",
+    "\n",
+    "I highly recommend reading the blog post [Sequence Modeling with CTC (2017)](https://distill.pub/2017/ctc/) very well-written blog post by Awni Hannun."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "e335hPmdtASZ"
+   },
+   "source": [
+    "Before we start, let's install both `datasets` and `transformers` from master. Also, we need the `torchaudio` and `librosa` package to load audio files and the `jiwer` to evaluate our fine-tuned model using the [word error rate (WER)](https://huggingface.co/metrics/wer) metric ${}^1$."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "id": "c8eh87Hoee5d"
+   },
+   "outputs": [],
+   "source": [
+    "# %%capture\n",
+    "# !pip install datasets==1.4.1\n",
+    "# # !pip install transformers==4.4.0\n",
+    "# !pip install torchaudio\n",
+    "# !pip install librosa\n",
+    "# !pip install jiwer"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# %%capture\n",
+    "# !pip install git+https://github.com/huggingface/transformers.git"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# %%capture\n",
+    "# !pip install wandb --upgrade"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "env: WANDB_ENTITY=wandb\n",
+      "env: WANDB_PROJECT=xlsr-nahuatl\n",
+      "env: WANDB_LOG_MODEL=true\n"
+     ]
+    }
+   ],
+   "source": [
+    "import os\n",
+    "import wandb\n",
+    "\n",
+    "# W&B company account\n",
+    "%env WANDB_ENTITY = wandb\n",
+    "entity = os.environ[\"WANDB_ENTITY\"]\n",
+    "\n",
+    "# Choose the public W&B project\n",
+    "%env WANDB_PROJECT = xlsr-nahuatl\n",
+    "project_name = os.environ[\"WANDB_PROJECT\"]\n",
+    "\n",
+    "# Log your trained model to W&B as an Artifact\n",
+    "%env WANDB_LOG_MODEL = true "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "Mn9swf6EQ9Vd"
+   },
+   "source": [
+    "\n",
+    "\n",
+    "\n",
+    "---\n",
+    "\n",
+    "${}^1$ In the [paper](https://arxiv.org/pdf/2006.13979.pdf), the model was evaluated using the phoneme error rate (PER), but by far the most common metric in ASR is the word error rate (WER). To keep this notebook as general as possible we decided to evaluate the model using WER."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Currently logged in as: \u001b[33mfastai_community\u001b[0m (use `wandb login --relogin` to force relogin)\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "wandb.login()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "0mW-C1Nt-j7k"
+   },
+   "source": [
+    "## Prepare Data, Tokenizer, Feature Extractor"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "BeBosnY9BH3e"
+   },
+   "source": [
+    "ASR models transcribe speech to text, which means that we both need a feature extractor that processes the speech signal to the model's input format, *e.g.* a feature vector, and a tokenizer that processes the model's output format to text. \n",
+    "\n",
+    "In 🤗 Transformers, the XLSR-Wav2Vec2 model is thus accompanied by both a tokenizer, called [Wav2Vec2CTCTokenizer](https://huggingface.co/transformers/master/model_doc/wav2vec2.html#wav2vec2ctctokenizer), and a feature extractor, called [Wav2Vec2FeatureExtractor](https://huggingface.co/transformers/master/model_doc/wav2vec2.html#wav2vec2featureextractor).\n",
+    "\n",
+    "Let's start by creating the tokenizer responsible for decoding the model's predictions."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "sEXEWEJGQPqD"
+   },
+   "source": [
+    "### Create Wav2Vec2CTCTokenizer"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "tWmMikuNEKl_"
+   },
+   "source": [
+    "The [pretrained Wav2Vec2 checkpoint]( ) maps the speech signal to a sequence of context representations as illustrated in the figure above. A fine-tuned XLSR-Wav2Vec2 checkpoint needs to map this sequence of context representations to its corresponding transcription so that a linear layer has to be added on top of the transformer block (shown in yellow). This linear layer is used to classifies each context representation to a token class analogous how, *e.g.*, after pretraining a linear layer is added on top of BERT's embeddings for further classification - *cf.* with *\"BERT\"* section of this [blog post](https://huggingface.co/blog/warm-starting-encoder-decoder).\n",
+    "\n",
+    "The output size of this layer corresponds to the number of tokens in the vocabulary, which does **not** depend on XLSR-Wav2Vec2's pretraining task, but only on the labeled dataset used for fine-tuning. So in the first step, we will take a look at Common Voice and define a vocabulary based on the dataset's transcriptions."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "idBczw8mWzgt"
+   },
+   "source": [
+    "First, let's go to [Common Voice](https://commonvoice.mozilla.org/en/datasets) and pick a language to fine-tune XLSR-Wav2Vec2 on. For this notebook, we will use Turkish. \n",
+    "\n",
+    "For each language-specific dataset, you can find a language code corresponding to your chosen language. On [Common Voice](https://commonvoice.mozilla.org/en/datasets), look for the field \"Version\". The language code then corresponds to the prefix before the underscore. For Turkish, *e.g.* the language code is `\"tr\"`.\n",
+    "\n",
+    "Great, now we can use 🤗 Datasets' simple API to download the data. The dataset name will be `\"common_voice\"`, the config name corresponds to the language code - `\"tr\"` in our case."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "bee4g9rpLxll"
+   },
+   "source": [
+    "Common Voice has many different splits including `invalidated`, which refers to data that was not rated as \"clean enough\" to be considered useful. In this notebook, we will only make use of the splits `\"train\"`, `\"validation\"` and `\"test\"`. \n",
+    "\n",
+    "Because the Turkish dataset is so small, we will merge both the validation and training data into a training dataset and simply use the test data for validation."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "##### nahuatl notes\n",
+    "\n",
+    "It seems that adding other languages to the trainning of the target language does help. So I have decided this time to take one and a half hour on trainning 50 epochs that means each epochs needs to be executed in around 2 minutes.\n",
+    "\n",
+    "With 2000 samples, it took around 3-6 hours. So taking 15 samples per second:\n",
+    "\n",
+    "* `15*60*90=81000`\n",
+    "* `15*60*60=54000`"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "##### nahuatl notes\n",
+    "\n",
+    "Create a nahhuatl dataset from the csv"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Using custom data configuration default-08b4e7b91c5bfd2a\n",
+      "Reusing dataset csv (/home/tyoc213/.cache/huggingface/datasets/csv/default-08b4e7b91c5bfd2a/0.0.0/2dc6629a9ff6b5697d82c25b73731dd440507a69cbce8b425db50b751e8fcfd0)\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "Dataset({\n",
+       "    features: ['main_file', 'chunk', 'start', 'end', 'duration', 'path', 'has_spanish', 'sentence'],\n",
+       "    num_rows: 136638\n",
+       "})"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from datasets import load_dataset, load_metric, Dataset\n",
+    "\n",
+    "common_voice_train = load_dataset('csv', data_files='nahuatl_slr90_by_sentence/sentences.csv', split=\"train\")\n",
+    "common_voice_train"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(176.1681610306425, 4.641500751696549, 0.1999999999999318, 211.803)"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "ds = pd.read_csv('nahuatl_slr90_by_sentence/sentences.csv')\n",
+    "ds['path'] = ('nahuatl_slr90_by_sentence/'+ds['path']).replace('flac', '')\n",
+    "\n",
+    "ds['duration'].sum()/60/60, ds['duration'].mean(), ds['duration'].min(), ds['duration'].max()"
+   ]
+  },
+  {
+   "attachments": {
+    "image.png": {
+     "image/png": "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"
+    }
+   },
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "##### nahuatl note\n",
+    "\n",
+    "Some audios are less than .5 seconds which `batch all {'path': 'nahuatl_slr90_by_sentence/0_109', 'sentence': 'ipa yehwa sah** '}` is `660.817-660.431=0.386` and causes this exception `ValueError: Audio must be have length greater than the block size`\n",
+    "\n",
+    "![image.png](attachment:image.png)\n",
+    "\n",
+    "##### nahuatl note\n",
+    "\n",
+    "Also filter out all the samples that has spanish in it, this will allow for only nahuatl and have less quantity of samples because processing them in `speech_file_to_array_loud_norm_fn` is slow on computer."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(32.00688685763889, 2.7633832814710892, 1.0009999999999764, 3.999000000000024)"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "ds = pd.read_csv('nahuatl_slr90_by_sentence/sentences.csv')\n",
+    "ds['path'] = ('nahuatl_slr90_by_sentence/'+ds['path']).replace('flac', '')\n",
+    "ds = ds.loc[ds['duration'] > 1]\n",
+    "ds = ds.loc[ds['duration'] < 4]\n",
+    "ds = ds.loc[ds['has_spanish'] == 0]\n",
+    "ds['duration'].sum()/60/60, ds['duration'].mean(), ds['duration'].min(), ds['duration'].max()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "41697"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(ds)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(23.250494444449995, 2.7900593333339994, 1.027000000000001, 3.999000000000024)"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# dsr = ds.sample(2000)\n",
+    "# dsr['duration'].sum()/60/60, dsr['duration'].mean(), dsr['duration'].min(), dsr['duration'].max()\n",
+    "dsr = ds.head(2000)\n",
+    "dsr_head = ds.head(1500)\n",
+    "dsr_tail = ds.head(500)\n",
+    "dsr_tail = dsr_tail.sample(100)\n",
+    "\n",
+    "# use only a fraction for faster epoch time\n",
+    "dsr = dsr_head.sample(500)\n",
+    "dsr['duration'].sum()/60, dsr['duration'].mean(), dsr['duration'].min(), dsr['duration'].max()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "##### nahuatl note\n",
+    "\n",
+    "Some files have nans when resample is made...\n",
+    "\n",
+    "##### nahuatl notes\n",
+    "\n",
+    "Because this is not a dataset from common voice, it needs to be made as https://discuss.huggingface.co/t/how-to-combine-local-data-files-with-an-official-dataset/4685/3 and each sample is exported as json"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#!ls /home/tyoc213/Documents/github/hf-xlsr-wav2vec2/nahuatl_slr90_by_sentence/"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from datasets import load_dataset, load_metric\n",
+    "\n",
+    "ds_train = ds[:1000]\n",
+    "ds_valid = ds[1500:]\n",
+    "\n",
+    "common_voice_train = Dataset.from_pandas(dsr) # load_dataset(\"json\", data_files=[f\"sample_{i}.json\" for i in range(0, train_total)], split=\"train\")\n",
+    "common_voice_train = common_voice_train.remove_columns(['main_file', 'chunk', 'start', 'end', 'duration', 'has_spanish', '__index_level_0__'])\n",
+    "common_voice_test = Dataset.from_pandas(dsr_tail)  # load_dataset(\"json\", data_files=[f\"sample_{i}.json\" for i in range(train_total, total_jsons)], split=\"train\")\n",
+    "common_voice_test = common_voice_test.remove_columns(['main_file', 'chunk', 'start', 'end', 'duration', 'has_spanish', '__index_level_0__'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Reusing dataset common_voice (/home/tyoc213/.cache/huggingface/datasets/common_voice/es/6.1.0/0041e06ab061b91d0a23234a2221e87970a19cf3a81b20901474cffffeb7869f)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 132 ms, sys: 8.86 ms, total: 141 ms\n",
+      "Wall time: 1.13 s\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "Dataset({\n",
+       "    features: ['path', 'sentence'],\n",
+       "    num_rows: 50\n",
+       "})"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "\n",
+    "import random\n",
+    "es = load_dataset(\"common_voice\", \"es\", split=\"train+validation\")\n",
+    "es = es.remove_columns(['client_id', 'up_votes', 'down_votes', 'age', 'gender', 'accent', 'locale', 'segment'])\n",
+    "\n",
+    "es = es.select(random.sample(range(len(es)), k=50))\n",
+    "\n",
+    "les = []\n",
+    "for i in range(len(es)):\n",
+    "    les.append({'path': es[i]['path'], 'sentence': es[i]['sentence']})\n",
+    "\n",
+    "es = pd.DataFrame(les)\n",
+    "es = Dataset.from_pandas(es)\n",
+    "es"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Reusing dataset common_voice (/home/tyoc213/.cache/huggingface/datasets/common_voice/de/6.1.0/0041e06ab061b91d0a23234a2221e87970a19cf3a81b20901474cffffeb7869f)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 155 ms, sys: 18.5 ms, total: 173 ms\n",
+      "Wall time: 870 ms\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "Dataset({\n",
+       "    features: ['path', 'sentence'],\n",
+       "    num_rows: 50\n",
+       "})"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "\n",
+    "import random\n",
+    "de = load_dataset(\"common_voice\", \"de\", split=\"train+validation\")\n",
+    "de = de.remove_columns(['client_id', 'up_votes', 'down_votes', 'age', 'gender', 'accent', 'locale', 'segment'])\n",
+    "\n",
+    "de = de.select(random.sample(range(len(de)), k=50))\n",
+    "\n",
+    "lde = []\n",
+    "for i in range(len(de)):\n",
+    "    lde.append({'path': de[i]['path'], 'sentence': de[i]['sentence']})\n",
+    "\n",
+    "de = pd.DataFrame(lde)\n",
+    "de = Dataset.from_pandas(de)\n",
+    "de"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(Dataset({\n",
+       "     features: ['path', 'sentence'],\n",
+       "     num_rows: 500\n",
+       " }),\n",
+       " Dataset({\n",
+       "     features: ['path', 'sentence'],\n",
+       "     num_rows: 100\n",
+       " }))"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "common_voice_train, common_voice_test"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(Dataset({\n",
+       "     features: ['path', 'sentence'],\n",
+       "     num_rows: 600\n",
+       " }),\n",
+       " Dataset({\n",
+       "     features: ['path', 'sentence'],\n",
+       "     num_rows: 100\n",
+       " }))"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import datasets\n",
+    "common_voice_train = datasets.concatenate_datasets([es, de, common_voice_train])\n",
+    "common_voice_train, common_voice_test"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "ri5y5N_HMANq"
+   },
+   "source": [
+    "Many ASR datasets only provide the target text, `'sentence'` for each audio file `'path'`. Common Voice actually provides much more information about each audio file, such as the `'accent'`, etc. However, we want to keep the notebook as general as possible, so that we will only consider the transcribed text for fine-tuning.\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "Go9Hq4e4NDT9"
+   },
+   "source": [
+    "Let's write a short function to display some random samples of the dataset and run it a couple of times to get a feeling for the transcriptions."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {
+    "id": "72737oog2F6U"
+   },
+   "outputs": [],
+   "source": [
+    "from datasets import ClassLabel\n",
+    "import random\n",
+    "import pandas as pd\n",
+    "from IPython.display import display, HTML\n",
+    "\n",
+    "def show_random_elements(dataset, num_examples=10):\n",
+    "    assert num_examples <= len(dataset), \"Can't pick more elements than there are in the dataset.\"\n",
+    "    picks = []\n",
+    "    for _ in range(num_examples):\n",
+    "        pick = random.randint(0, len(dataset)-1)\n",
+    "        while pick in picks:\n",
+    "            pick = random.randint(0, len(dataset)-1)\n",
+    "        picks.append(pick)\n",
+    "    \n",
+    "    df = pd.DataFrame(dataset[picks])\n",
+    "    display(HTML(df.to_html()))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 669
+    },
+    "id": "K_JUmf3G3b9S",
+    "outputId": "a8fe6d21-b0ce-4d5b-e3a2-abe08ae551f7"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>sentence</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>pos tik..., tikichkwayah yo:n ma:pahkamoh.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>Yo:n ye:kte:kokoh ke:meh, ke:meh a:lsimit</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>¿Wa:n ka:walpox?</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>Ke:mah, neli tikokototskeh para tikmahkeh.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>Iwki nikchi:wa, nikita kwaltia ya pos nikpa:ka ya wa:n ni...,</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>semi tsohtsope:k, ke:mah.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>xa: tikitaka ya no:.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>¿Kati:yeh xiwit, yo:n ke:ní:w tikto:ka:itiah?</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>tepitsi:n wehwei ke:meh kahbe:nxiwit,</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>wa:n ompa kikwah nijó:n iteyo de n' xo:no:t</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10</th>\n",
+       "      <td>Wa:n onkak n' tein xohxole:wih.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>11</th>\n",
+       "      <td>Die Garten-Entwürfe zeigen die typischen Beet-Reihungen der Renaissance-Gärten.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>12</th>\n",
+       "      <td>Estudió Lingüística y Literatura Hispánica en la Pontificia Universidad Católica del Perú.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>13</th>\n",
+       "      <td>Además, se elevó la relación de compresión del motor utilizando nuevos pistones.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>14</th>\n",
+       "      <td>Yehwa i:n ke:mah, a:mo, i:n a:mo we:lik.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>15</th>\n",
+       "      <td>nochi yehwa i:n de n' xiwtsitsi:n, ta:taman nochi tikmatih</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>16</th>\n",
+       "      <td>Ninemik To:nali:x, nimoskaltih.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>17</th>\n",
+       "      <td>Soh mah se: kito:ka sah, ke:meh nimitsilia ne: ohti onkak, ne: ohte:noh</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>18</th>\n",
+       "      <td>Wa:n i:n seki kowitomtmeh itech kowit mota:liah,</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>19</th>\n",
+       "      <td>Wa:n a:mo semi wehkapantia, tsikitsi:n ihkó:n, tsikitsitsi:n.Ta:lpantsitsi:n mochi:wa.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>20</th>\n",
+       "      <td>Die Bahn wird nicht ausgenutzt.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>21</th>\n",
+       "      <td>wa:n timoliah tehwa:n ke tiweliskeh.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>22</th>\n",
+       "      <td>Tres nuevos equipos se integran a esta categoría en esta temporada.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>23</th>\n",
+       "      <td>Earl of Pembroke und von dessen Gemahlin Isabel de Clare.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>24</th>\n",
+       "      <td>A:man na:nah xte:chtapowi ne: i:n</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>25</th>\n",
+       "      <td>A:mo te:pahwih nió:n tei, ne: tsope:k ne:n kowtet.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>26</th>\n",
+       "      <td>Nochi iwa:n, iwa:n ya imekayo wa:n xiwit, mah se: kisenta:li.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>27</th>\n",
+       "      <td>Wa:n, wa:n no: cha:wak.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>28</th>\n",
+       "      <td>para ne: ne:stiw a, ne:stiw a kihto:s no:pá:n \"nika:n yetok a,</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>29</th>\n",
+       "      <td>Pero pueden ser empleadas para otros usos.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>30</th>\n",
+       "      <td>se: taki:tskil tikwiti wa:n tikmolo:ntia wa:n</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>31</th>\n",
+       "      <td>Pos...pos de te:n tikmatih, yehwa sah neji:ni de n' xiwtsí:n de n' tsope:likxiwit.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32</th>\n",
+       "      <td>Tsikitsitsi:n.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>33</th>\n",
+       "      <td>Entó:s ki:sa ya tech n' koxta:l oso ne: ka:mpa se: ka:ta:lihtok.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>34</th>\n",
+       "      <td>Wa:n nehwa m'pahtih. Mm.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>35</th>\n",
+       "      <td>Neli, ke:meh yo:n ka:mpa onkak, pos se: kwelita kwaltsi:n no:.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>36</th>\n",
+       "      <td>\"¿Ke:yeh m'ijos n' a:xka:n tehwa:n,</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>37</th>\n",
+       "      <td>Chichinawi wa:n miak mote:ma ne:n, ne:n kownex.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>38</th>\n",
+       "      <td>Zusammen mit Garrett Tierney und Brian Lane gründete er zunächst The Rookie Lot.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>39</th>\n",
+       "      <td>Soh ixo:chio a:it ke:yeh nijó:n chi:chi:ltik.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>40</th>\n",
+       "      <td>Panxa:ltik tepistsi:n ke:meh i:n wa:xin. Mm.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>41</th>\n",
+       "      <td>Entó:s tetampa ya pos a:mo wel tiki:xti:tih</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>42</th>\n",
+       "      <td>Oso itech tet.Itech kowit, oso te..., te..., itech tet mochi:wa.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>43</th>\n",
+       "      <td>Nejó:n ihkó:n tahtamati</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>44</th>\n",
+       "      <td>Pos nimono:tsa niCelina González Nazario.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>45</th>\n",
+       "      <td>wa:n pané: achi pototik n' ipane:wayo,</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>46</th>\n",
+       "      <td>Pos yeh tsikitsitsi:n wa:n kahkana:wak.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>47</th>\n",
+       "      <td>pisi:ltik wa:n wehwei. Yehwa n' ekin tne:chilwihtoya.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>48</th>\n",
+       "      <td>tikwitih wa:n nikmana.A:, ke:mah.</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>49</th>\n",
+       "      <td>komohkó:n kilpihkeh ka:sá: kahfe:ntah wa:n onkak, no: kikwa ata yo:n xiwit, kikwa no:.</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "show_random_elements(common_voice_train.remove_columns([\"path\"]), num_examples=50)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "fowcOllGNNju"
+   },
+   "source": [
+    "Alright! The transcriptions look fairly clean. Having translated the transcribed sentences (I'm sadly not a native speaker in Turkish), it seems that the language corresponds more to written text than noisy dialogue. This makes sense taking into account that [Common Voice](https://huggingface.co/datasets/common_voice) is a crowd-sourced read speech corpus."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "vq7OR50LN49m"
+   },
+   "source": [
+    "We can see that the transcriptions contain some special characters, such as `,.?!;:`. Without a language model, it is much harder to classify speech chunks to such special characters because they don't really correspond to a characteristic sound unit. *E.g.*, the letter `\"s\"` has a more or less clear sound, whereas the special character `\".\"` does not.\n",
+    "Also in order to understand the meaning of a speech signal, it is usually not necessary to include special characters in the transcription.\n",
+    "\n",
+    "In addition, we normalize the text to only have lower case letters and append a word separator token at the end."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "additional chars to remove = ( ) -"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "##### Nahuatl note\n",
+    "\n",
+    "`:` is for indicating a long vowel, we should delete that? or convert to other char? like `o: = ó`?"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {
+    "id": "svKzVJ_hQGK6"
+   },
+   "outputs": [],
+   "source": [
+    "import re\n",
+    "#chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\:\\\"\\“\\%\\‘\\”\\�\\(\\)\\-]'\n",
+    "chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\\"\\“\\%\\‘\\”\\�\\(\\)\\-]'\n",
+    "\n",
+    "def remove_special_characters(batch):\n",
+    "    batch[\"sentence\"] = re.sub(chars_to_ignore_regex, '', batch[\"sentence\"]).lower() + \" \"\n",
+    "    return batch"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 117,
+     "referenced_widgets": [
+      "92a35db69bbf4ad6af44c53aa3870be5",
+      "389e43e47a734193a507817ebad955f7",
+      "b94e374d92c146009447c3827b977267",
+      "1f1faa7b986e475c9e6839b2e7b55c74",
+      "4ff7ccffc36a4a0f93031f5cdc3b718d",
+      "b177a8cb85a24b88ab6d56205b630f1d",
+      "2ca2f397c4ef405bba27ae2b1415cada",
+      "b320306eaf264ad9872d507a1a1cb2da",
+      "cc9c1e00c2d34516b8fd9edff96bb0d8",
+      "6abfbe44a1bd4518b41f5f53f920e936",
+      "33c92b5afd1d4b6d88016aabfb434194",
+      "998676d59f9c464e8463d65baad6448b",
+      "45f0a2f361da4608bc8314a27657a56c",
+      "3dc9ea77b842455a91f00e9ca9f41948",
+      "7bf5b2b625764f63ad57a360c3fd0a61",
+      "7b4cfd2b448643b8a4409dd612aef0d1"
+     ]
+    },
+    "id": "XIHocAuTQbBR",
+    "outputId": "cc1a70b2-7b4d-410b-f997-1f1c47c3c9e5"
+   },
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "b2a4ebe8dd2e4c2f850d68415d2f323d",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "HBox(children=(FloatProgress(value=0.0, max=600.0), HTML(value='')))"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "1aa6a8a0e5c34338818a6638e1a7ac01",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "HBox(children=(FloatProgress(value=0.0), HTML(value='')))"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "CPU times: user 493 ms, sys: 114 ms, total: 607 ms\n",
+      "Wall time: 627 ms\n"
+     ]
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "common_voice_train = common_voice_train.map(remove_special_characters)\n",
+    "common_voice_test = common_voice_test.map(remove_special_characters)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 359
+    },
+    "id": "RBDRAAYxRE6n",
+    "outputId": "c3a72eaa-8ddc-4283-ccb8-52e50215b84d"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>sentence</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>¿wa:n ixiwyo ahalaxtik xaxakachtik</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>ke:meh kintsi:n i:n new</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>¿n yo:n xiwit no: onkak n' tein ista:kajá</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>wa:n wa:n no: cha:wak</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>tepitsi:n wehwei ke:meh kahbe:nxiwit</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>se: tataxiskwi se: mokwa:te:kilia no:chi se: iyo:li:ka:n se: iyo:lpan</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>ki:sa pané: tixti ne: n' ihtik yo:n okwiltsi:n</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>el condado recibe su nombre en honor a jesse lee reno</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>yo:n porin t'tatsiwiliah para timo para timota:li:skeh tehwa:n t'chihchi:waskeh pahti</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>tras el incidente se recuperó y salió de la cancha por sus propios medios</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "show_random_elements(common_voice_train.remove_columns([\"path\"]))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "jwfaptH5RJwA"
+   },
+   "source": [
+    "Good! This looks better. We have removed most special characters from transcriptions and normalized them to lower-case only.\n",
+    "\n",
+    "In CTC, it is common to classify speech chunks into letters, so we will do the same here. \n",
+    "Let's extract all distinct letters of the training and test data and build our vocabulary from this set of letters.\n",
+    "\n",
+    "We write a mapping function that concatenates all transcriptions into one long transcription and then transforms the string into a set of chars. \n",
+    "It is important to pass the argument `batched=True` to the `map(...)` function so that the mapping function has access to all transcriptions at once."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {
+    "id": "LwCshNbbeRZR"
+   },
+   "outputs": [],
+   "source": [
+    "def extract_all_chars(batch):\n",
+    "  all_text = \" \".join(batch[\"sentence\"])\n",
+    "  vocab = list(set(all_text))\n",
+    "  return {\"vocab\": [vocab], \"all_text\": [all_text]}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 117,
+     "referenced_widgets": [
+      "304e9130c12f4110941bfbd3db49a28c",
+      "5e6bae23461b4378b6e5fc890fe6bc97",
+      "75e00c38605f44cfb584067db1160349",
+      "8c07a528fc4a4e108b393ab117fe2e46",
+      "c01aca3229a24d41841be2b4a3a65bcc",
+      "73ecbfc3c5c5456bb42e19b8a34b1576",
+      "813fc95246034f5cb9e5198897b4ed42",
+      "8bb78a89ff81400791e3005098fdcb94",
+      "bd0958ea97b141b1aca367c71721c549",
+      "0354ab33471e4c34a0c1b3c062bcd6bb",
+      "d080668299ef42fabb8ab6fbcf329cea",
+      "aafd4b2c56db43378c4627797665db17",
+      "b0f3a205ad4546188fc6e7e7cf96ab32",
+      "f972527479e74337a98f236ed018ae1d",
+      "ccb720bf256e42f7b0251494ccb7741f",
+      "ad428686450f4ebdb50a0356b2e5a8c4"
+     ]
+    },
+    "id": "_m6uUjjcfbjH",
+    "outputId": "75a1a23f-a9c7-4c8b-8777-dad120a9aa9a"
+   },
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "bb82c9c8e8b448cd9220aff6f1ac0ee4",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "HBox(children=(FloatProgress(value=0.0, max=1.0), HTML(value='')))"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "77000a5ba096427cbc877893e12525d6",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "HBox(children=(FloatProgress(value=0.0, max=1.0), HTML(value='')))"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "vocab_train = common_voice_train.map(extract_all_chars, batched=True, batch_size=-1, keep_in_memory=True, remove_columns=common_voice_train.column_names)\n",
+    "vocab_test = common_voice_test.map(extract_all_chars, batched=True, batch_size=-1, keep_in_memory=True, remove_columns=common_voice_test.column_names)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "7oVgE8RZSJNP"
+   },
+   "source": [
+    "Now, we create the union of all distinct letters in the training dataset and test dataset and convert the resulting list into an enumerated dictionary."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {
+    "id": "aQfneNsmlJI0"
+   },
+   "outputs": [],
+   "source": [
+    "vocab_list = list(set(vocab_train[\"vocab\"][0]) | set(vocab_test[\"vocab\"][0]))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "_0kRndSvqaKk",
+    "outputId": "29f5d23f-75b1-44d0-9975-87f9ec4c0aa5"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[' ',\n",
+       " \"'\",\n",
+       " ':',\n",
+       " '[',\n",
+       " ']',\n",
+       " 'a',\n",
+       " 'b',\n",
+       " 'c',\n",
+       " 'd',\n",
+       " 'e',\n",
+       " 'f',\n",
+       " 'g',\n",
+       " 'h',\n",
+       " 'i',\n",
+       " 'j',\n",
+       " 'k',\n",
+       " 'l',\n",
+       " 'm',\n",
+       " 'n',\n",
+       " 'o',\n",
+       " 'p',\n",
+       " 'q',\n",
+       " 'r',\n",
+       " 's',\n",
+       " 't',\n",
+       " 'u',\n",
+       " 'v',\n",
+       " 'w',\n",
+       " 'x',\n",
+       " 'y',\n",
+       " 'z',\n",
+       " '¿',\n",
+       " 'ß',\n",
+       " 'á',\n",
+       " 'ä',\n",
+       " 'é',\n",
+       " 'í',\n",
+       " 'ñ',\n",
+       " 'ó',\n",
+       " 'ö',\n",
+       " 'ú',\n",
+       " 'ü',\n",
+       " '„']"
+      ]
+     },
+     "execution_count": 27,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "vocab_dict = {v: k for k, v in enumerate(vocab_list)}\n",
+    "sorted(vocab_dict.keys())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "JOSzbvs9SXT1"
+   },
+   "source": [
+    "Cool, we see that all letters of the alphabet occur in the dataset (which is not really surprising) and we also extracted the special characters `\" \"` and `'`. Note that we did not exclude those special characters because: \n",
+    "\n",
+    "- The model has to learn to predict when a word is finished or else the model prediction would always be a sequence of chars which would make it impossible to separate words from each other.\n",
+    "- From the transcriptions above it seems that words that include an apostrophe, such as `maktouf'un` do exist in Turkish, so I decided to keep the apostrophe in the dataset. This might be a wrong assumption though.\n",
+    "\n",
+    "One should always keep in mind that the data-preprocessing is a very important step before training your model. E.g., we don't want our model to differentiate between `a` and `A` just because we forgot to normalize the data. The difference between `a` and `A` does not depend on the \"sound\" of the letter at all, but more on grammatical rules - *e.g.* use a capitalized letter at the beginning of the sentence. So it is sensible to remove the difference between capitalized and non-capitalized letters so that the model has an easier time learning to transcribe speech. \n",
+    "\n",
+    "It is always advantageous to get help from a native speaker of the language you would like to transcribe to verify whether the assumptions you made are sensible, *e.g.* I should have made sure that keeping `'`, but removing other special characters is a sensible choice for Turkish. "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "b1fBRCn-TRaO"
+   },
+   "source": [
+    "To make it clearer that `\" \"` has its own token class, we give it a more visible character `|`. In addition, we also add an \"unknown\" token so that the model can later deal with characters not encountered in Common Voice's training set. \n",
+    "\n",
+    "Finally, we also add a padding token that corresponds to CTC's \"*blank token*\". The \"blank token\" is a core component of the CTC algorithm. For more information, please take a look at the \"Alignment\" section [here](https://distill.pub/2017/ctc/)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {
+    "id": "npbIbBoLgaFX"
+   },
+   "outputs": [],
+   "source": [
+    "vocab_dict[\"|\"] = vocab_dict[\" \"]\n",
+    "del vocab_dict[\" \"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "znF0bNunsjbl",
+    "outputId": "6dd50862-f4c5-4a05-87a7-da03d157e30e"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "45"
+      ]
+     },
+     "execution_count": 29,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "vocab_dict[\"[UNK]\"] = len(vocab_dict)\n",
+    "vocab_dict[\"[PAD]\"] = len(vocab_dict)\n",
+    "len(vocab_dict)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'x': 0,\n",
+       " 'v': 1,\n",
+       " ']': 2,\n",
+       " 'í': 3,\n",
+       " ':': 4,\n",
+       " 'k': 5,\n",
+       " 'y': 6,\n",
+       " 'ö': 7,\n",
+       " \"'\": 8,\n",
+       " 'h': 9,\n",
+       " '¿': 11,\n",
+       " 'ñ': 12,\n",
+       " 'n': 13,\n",
+       " 'ü': 14,\n",
+       " 'ä': 15,\n",
+       " 't': 16,\n",
+       " 'm': 17,\n",
+       " 's': 18,\n",
+       " 'g': 19,\n",
+       " 'á': 20,\n",
+       " 'z': 21,\n",
+       " 'o': 22,\n",
+       " 'w': 23,\n",
+       " '[': 24,\n",
+       " 'r': 25,\n",
+       " 'b': 26,\n",
+       " 'ß': 27,\n",
+       " 'd': 28,\n",
+       " 'ó': 29,\n",
+       " 'i': 30,\n",
+       " 'e': 31,\n",
+       " '„': 32,\n",
+       " 'ú': 33,\n",
+       " 'c': 34,\n",
+       " 'f': 35,\n",
+       " 'p': 36,\n",
+       " 'a': 37,\n",
+       " 'l': 38,\n",
+       " 'q': 39,\n",
+       " 'j': 40,\n",
+       " 'u': 41,\n",
+       " 'é': 42,\n",
+       " '|': 10,\n",
+       " '[UNK]': 43,\n",
+       " '[PAD]': 44}"
+      ]
+     },
+     "execution_count": 30,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "vocab_dict"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "SFPGfet8U5sL"
+   },
+   "source": [
+    "Cool, now our vocabulary is complete and consists of 39 tokens, which means that the linear layer that we will add on top of the pretrained XLSR-Wav2Vec2 checkpoint will have an output dimension of 39."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "1CujRgBNVRaD"
+   },
+   "source": [
+    "Let's now save the vocabulary as a json file."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {
+    "id": "ehyUoh9vk191"
+   },
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "with open('vocab.json', 'w') as vocab_file:\n",
+    "    json.dump(vocab_dict, vocab_file)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "SHJDaKlIVVim"
+   },
+   "source": [
+    "In a final step, we use the json file to instantiate an object of the `Wav2Vec2CTCTokenizer` class."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "metadata": {
+    "id": "xriFGEWQkO4M"
+   },
+   "outputs": [],
+   "source": [
+    "from transformers import Wav2Vec2CTCTokenizer\n",
+    "\n",
+    "tokenizer = Wav2Vec2CTCTokenizer(\"./vocab.json\", unk_token=\"[UNK]\", pad_token=\"[PAD]\", word_delimiter_token=\"|\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "KvL12DrNV4cx"
+   },
+   "source": [
+    "Next, we will create the feature extractor."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "mYcIiR2FQ96i"
+   },
+   "source": [
+    "### Create XLSR-Wav2Vec2 Feature Extractor"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "Y6mDEyW719rx"
+   },
+   "source": [
+    "Speech is a continuous signal and to be treated by computers, it first has to be discretized, which is usually called **sampling**. The sampling rate hereby plays an important role in that it defines how many data points of the speech signal are measured per second. Therefore, sampling with a higher sampling rate results in a better approximation of the *real* speech signal but also necessitates more values per second.\n",
+    "\n",
+    "A pretrained checkpoint expects its input data to have been sampled more or less from the same distribution as the data it was trained on. The same speech signals sampled at two different rates have a very different distribution, *e.g.*, doubling the sampling rate results in data points being twice as long. Thus, \n",
+    "before fine-tuning a pretrained checkpoint of an ASR model, it is crucial to verify that the sampling rate of the data that was used to pretrain the model matches the sampling rate of the dataset used to fine-tune the model.\n",
+    "\n",
+    "XLSR-Wav2Vec2 was pretrained on the audio data of [Babel](https://huggingface.co/datasets/librispeech_asr), \n",
+    "[Multilingual LibriSpeech (MLS)](https://ai.facebook.com/blog/a-new-open-data-set-for-multilingual-speech-research/), and [Common Voice](https://huggingface.co/datasets/common_voice). Most of those datasets were sampled at 16kHz, so that Common Voice, sampled at 48kHz, has to be downsampled to 16kHz for training. Therefore, we will have to downsample our fine-tuning data to 16kHz in the following.\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "KuUbPW7oV-B5"
+   },
+   "source": [
+    "A XLSR-Wav2Vec2 feature extractor object requires the following parameters to be instantiated:\n",
+    "\n",
+    "- `feature_size`: Speech models take a sequence of feature vectors as an input. While the length of this sequence obviously varies, the feature size should not. In the case of Wav2Vec2, the feature size is 1 because the model was trained on the raw speech signal ${}^2$.\n",
+    "- `sampling_rate`: The sampling rate at which the model is trained on.\n",
+    "- `padding_value`: For batched inference, shorter inputs need to be padded with a specific value\n",
+    "- `do_normalize`: Whether the input should be *zero-mean-unit-variance* normalized or not. Usually, speech models perform better when normalizing the input\n",
+    "- `return_attention_mask`: Whether the model should make use of an `attention_mask` for batched inference. In general, XLSR-Wav2Vec2 models should **always** make use of the `attention_mask`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "metadata": {
+    "id": "kAR0-2KLkopp"
+   },
+   "outputs": [],
+   "source": [
+    "from transformers import Wav2Vec2FeatureExtractor\n",
+    "\n",
+    "feature_extractor = Wav2Vec2FeatureExtractor(feature_size=1, sampling_rate=16000, padding_value=0.0, do_normalize=True, return_attention_mask=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "qUETetgqYC3W"
+   },
+   "source": [
+    "Great, XLSR-Wav2Vec2's feature extraction pipeline is thereby fully defined!\n",
+    "\n",
+    "To make the usage of XLSR-Wav2Vec2 as user-friendly as possible, the feature extractor and tokenizer are *wrapped* into a single `Wav2Vec2Processor` class so that one only needs a `model` and `processor` object."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "metadata": {
+    "id": "KYZtoW-tlZgl"
+   },
+   "outputs": [],
+   "source": [
+    "from transformers import Wav2Vec2Processor\n",
+    "\n",
+    "processor = Wav2Vec2Processor(feature_extractor=feature_extractor, tokenizer=tokenizer)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "fTfFDSS0YfMN"
+   },
+   "source": [
+    "If one wants to re-use the just created processor and the fine-tuned model of this notebook, one can mount his/her google drive to the notebook and save all relevant files there. To do so, please uncomment the following lines. \n",
+    "\n",
+    "We will give the fine-tuned model the name `\"wav2vec2-large-xlsr-nahuatl-demo\"`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "yq7Bzuzz4zjQ",
+    "outputId": "419faa94-b24f-4044-877a-ce511978c97d"
+   },
+   "outputs": [],
+   "source": [
+    "# from google.colab import drive\n",
+    "# drive.mount('/content/gdrive/')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "metadata": {
+    "id": "Par9rpypPsml"
+   },
+   "outputs": [],
+   "source": [
+    "def the_name(append=''):\n",
+    "    MAIN_NAME = 'final0-wav2vec2-large-xlsr-nahuatl-es-de-'\n",
+    "    return '%s%s'%(MAIN_NAME,append)\n",
+    "processor.save_pretrained(the_name())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "wav2vec2-large-xlsr-25.6m-nahuatl-es-de:\r\n",
+      "total 5296\r\n",
+      "drwxrwxr-x  2 tyoc213 tyoc213    4096 mar 28 12:14 .\r\n",
+      "drwxrwxr-x 26 tyoc213 tyoc213 5398528 mar 28 17:03 ..\r\n",
+      "-rw-rw-r--  1 tyoc213 tyoc213     158 mar 28 14:59 preprocessor_config.json\r\n",
+      "-rw-rw-r--  1 tyoc213 tyoc213      85 mar 28 14:59 special_tokens_map.json\r\n",
+      "-rw-rw-r--  1 tyoc213 tyoc213     138 mar 28 14:59 tokenizer_config.json\r\n",
+      "-rw-rw-r--  1 tyoc213 tyoc213     435 mar 28 14:59 vocab.json\r\n",
+      "\r\n",
+      "wav2vec2-large-xlsr-25.6m-nahuatl-es-de-one:\r\n",
+      "total 5284\r\n",
+      "drwxrwxr-x  3 tyoc213 tyoc213    4096 mar 28 16:57 .\r\n",
+      "drwxrwxr-x 26 tyoc213 tyoc213 5398528 mar 28 17:03 ..\r\n",
+      "drwxrwxr-x  2 tyoc213 tyoc213    4096 mar 28 16:37 checkpoint-1500\r\n",
+      "\r\n",
+      "wav2vec2-large-xlsr-nahuatl-1_5K-es-de:\r\n",
+      "total 5296\r\n",
+      "drwxrwxr-x  2 tyoc213 tyoc213    4096 mar 28 09:28 .\r\n",
+      "drwxrwxr-x 26 tyoc213 tyoc213 5398528 mar 28 17:03 ..\r\n",
+      "-rw-rw-r--  1 tyoc213 tyoc213     158 mar 28 09:53 preprocessor_config.json\r\n",
+      "-rw-rw-r--  1 tyoc213 tyoc213      85 mar 28 09:53 special_tokens_map.json\r\n",
+      "-rw-rw-r--  1 tyoc213 tyoc213     138 mar 28 09:53 tokenizer_config.json\r\n",
+      "-rw-rw-r--  1 tyoc213 tyoc213     446 mar 28 09:53 vocab.json\r\n",
+      "\r\n",
+      "wav2vec2-large-xlsr-nahuatl-1_5K-es-de-one:\r\n",
+      "total 5284\r\n",
+      "drwxrwxr-x  3 tyoc213 tyoc213    4096 mar 28 12:03 .\r\n",
+      "drwxrwxr-x 26 tyoc213 tyoc213 5398528 mar 28 17:03 ..\r\n",
+      "drwxrwxr-x  2 tyoc213 tyoc213    4096 mar 28 12:03 checkpoint-1525\r\n",
+      "\r\n",
+      "wav2vec2-large-xlsr-nahuatl-demo:\r\n",
+      "total 5308\r\n",
+      "drwxrwxr-x  5 tyoc213 tyoc213    4096 mar 27 10:49 .\r\n",
+      "drwxrwxr-x 26 tyoc213 tyoc213 5398528 mar 28 17:03 ..\r\n",
+      "drwxrwxr-x  2 tyoc213 tyoc213    4096 mar 27 10:43 checkpoint-1400\r\n",
+      "-rw-rw-r--  1 tyoc213 tyoc213     158 mar 27 15:21 preprocessor_config.json\r\n",
+      "drwxrwxr-x  4 tyoc213 tyoc213    4096 mar 27 02:33 second-train\r\n",
+      "-rw-rw-r--  1 tyoc213 tyoc213      85 mar 27 15:21 special_tokens_map.json\r\n",
+      "drwxrwxr-x  2 tyoc213 tyoc213    4096 mar 27 09:41 third-train\r\n",
+      "-rw-rw-r--  1 tyoc213 tyoc213     138 mar 27 15:21 tokenizer_config.json\r\n",
+      "-rw-rw-r--  1 tyoc213 tyoc213     448 mar 27 15:21 vocab.json\r\n",
+      "\r\n",
+      "wav2vec2-large-xlsr-nahuatl-demo-es-de:\r\n",
+      "total 5296\r\n",
+      "drwxrwxr-x  2 tyoc213 tyoc213    4096 mar 27 15:22 .\r\n",
+      "drwxrwxr-x 26 tyoc213 tyoc213 5398528 mar 28 17:03 ..\r\n",
+      "-rw-rw-r--  1 tyoc213 tyoc213     158 mar 27 16:04 preprocessor_config.json\r\n",
+      "-rw-rw-r--  1 tyoc213 tyoc213      85 mar 27 16:04 special_tokens_map.json\r\n",
+      "-rw-rw-r--  1 tyoc213 tyoc213     138 mar 27 16:04 tokenizer_config.json\r\n",
+      "-rw-rw-r--  1 tyoc213 tyoc213     435 mar 27 16:04 vocab.json\r\n",
+      "\r\n",
+      "wav2vec2-large-xlsr-nahuatl-es-de:\r\n",
+      "total 5296\r\n",
+      "drwxrwxr-x  2 tyoc213 tyoc213    4096 mar 27 16:07 .\r\n",
+      "drwxrwxr-x 26 tyoc213 tyoc213 5398528 mar 28 17:03 ..\r\n",
+      "-rw-rw-r--  1 tyoc213 tyoc213     158 mar 28 01:41 preprocessor_config.json\r\n",
+      "-rw-rw-r--  1 tyoc213 tyoc213      85 mar 28 01:41 special_tokens_map.json\r\n",
+      "-rw-rw-r--  1 tyoc213 tyoc213     138 mar 28 01:41 tokenizer_config.json\r\n",
+      "-rw-rw-r--  1 tyoc213 tyoc213     414 mar 28 01:41 vocab.json\r\n",
+      "\r\n",
+      "wav2vec2-large-xlsr-nahuatl-es-de-cinco:\r\n",
+      "total 5284\r\n",
+      "drwxrwxr-x  3 tyoc213 tyoc213    4096 mar 27 23:53 .\r\n",
+      "drwxrwxr-x 26 tyoc213 tyoc213 5398528 mar 28 17:03 ..\r\n",
+      "drwxrwxr-x  2 tyoc213 tyoc213    4096 mar 27 22:56 checkpoint-25\r\n",
+      "\r\n",
+      "wav2vec2-large-xlsr-nahuatl-es-de-cuatro:\r\n",
+      "total 5284\r\n",
+      "drwxrwxr-x  3 tyoc213 tyoc213    4096 mar 27 22:47 .\r\n",
+      "drwxrwxr-x 26 tyoc213 tyoc213 5398528 mar 28 17:03 ..\r\n",
+      "drwxrwxr-x  2 tyoc213 tyoc213    4096 mar 27 22:47 checkpoint-650\r\n",
+      "\r\n",
+      "wav2vec2-large-xlsr-nahuatl-es-de-dos:\r\n",
+      "total 5284\r\n",
+      "drwxrwxr-x  3 tyoc213 tyoc213    4096 mar 27 19:21 .\r\n",
+      "drwxrwxr-x 26 tyoc213 tyoc213 5398528 mar 28 17:03 ..\r\n",
+      "drwxrwxr-x  2 tyoc213 tyoc213    4096 mar 27 18:48 checkpoint-550\r\n",
+      "\r\n",
+      "wav2vec2-large-xlsr-nahuatl-es-de-one:\r\n",
+      "total 5280\r\n",
+      "drwxrwxr-x  2 tyoc213 tyoc213    4096 mar 27 19:57 .\r\n",
+      "drwxrwxr-x 26 tyoc213 tyoc213 5398528 mar 28 17:03 ..\r\n",
+      "\r\n",
+      "wav2vec2-large-xlsr-nahuatl-es-deone:\r\n",
+      "total 5284\r\n",
+      "drwxrwxr-x  3 tyoc213 tyoc213    4096 mar 27 18:01 .\r\n",
+      "drwxrwxr-x 26 tyoc213 tyoc213 5398528 mar 28 17:03 ..\r\n",
+      "drwxrwxr-x  2 tyoc213 tyoc213    4096 mar 27 18:01 checkpoint-950\r\n",
+      "\r\n",
+      "wav2vec2-large-xlsr-nahuatl-es-de-seis66:\r\n",
+      "total 5284\r\n",
+      "drwxrwxr-x  3 tyoc213 tyoc213    4096 mar 28 01:33 .\r\n",
+      "drwxrwxr-x 26 tyoc213 tyoc213 5398528 mar 28 17:03 ..\r\n",
+      "drwxrwxr-x  2 tyoc213 tyoc213    4096 mar 28 01:28 checkpoint-625\r\n",
+      "\r\n",
+      "wav2vec2-large-xlsr-nahuatl-es-de-siete77:\r\n",
+      "total 5284\r\n",
+      "drwxrwxr-x  3 tyoc213 tyoc213    4096 mar 28 02:15 .\r\n",
+      "drwxrwxr-x 26 tyoc213 tyoc213 5398528 mar 28 17:03 ..\r\n",
+      "drwxrwxr-x  2 tyoc213 tyoc213    4096 mar 28 01:52 checkpoint-25\r\n",
+      "\r\n",
+      "wav2vec2-large-xlsr-nahuatl-es-de-tres:\r\n",
+      "total 5284\r\n",
+      "drwxrwxr-x  3 tyoc213 tyoc213    4096 mar 27 21:35 .\r\n",
+      "drwxrwxr-x 26 tyoc213 tyoc213 5398528 mar 28 17:03 ..\r\n",
+      "drwxrwxr-x  2 tyoc213 tyoc213    4096 mar 27 21:29 checkpoint-925\r\n"
+     ]
+    }
+   ],
+   "source": [
+    "!ls -la wav2vec*"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "DrKnYuvDIoOO"
+   },
+   "source": [
+    "Next, we can prepare the dataset."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "YFmShnl7RE35"
+   },
+   "source": [
+    "### Preprocess Data\n",
+    "\n",
+    "So far, we have not looked at the actual values of the speech signal but just kept the path to its file in the dataset. `XLSR-Wav2Vec2` expects the audio file in the format of a 1-dimensional array, so in the first step, let's load all audio files into the dataset object.\n",
+    "\n",
+    "Let's first check the serialization format of the downloaded audio files by looking at the first training sample."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "TTCS7W6XJ9BG",
+    "outputId": "9c3b8cc0-3bcd-43fe-87ca-2825239b365a"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'path': '/home/tyoc213/.cache/huggingface/datasets/downloads/extracted/23afbf80948a799bdd449b33e1e2dec4e2c3a6f484ca9d51877da3a04ecec770/cv-corpus-6.1-2020-12-11/es/clips/common_voice_es_20298979.mp3',\n",
+       " 'sentence': 'es autora de una serie de artículos históricos sobre clay county misuri '}"
+      ]
+     },
+     "execution_count": 38,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "common_voice_train[0]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "wSBIGEiaKHMn"
+   },
+   "source": [
+    "Alright, the audio file is saved in the `.mp3` format. The `.mp3` format is usually not the easiest format to deal with. We found that the [`torchaudio`](https://pytorch.org/audio/stable/index.html) library works best for reading in `.mp3` data. \n",
+    "\n",
+    "An audio file usually stores both its values and the sampling rate with which the speech signal was digitalized. We want to store both in the dataset and write a `map(...)` function accordingly."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "metadata": {
+    "id": "al9Luo4LPpwJ"
+   },
+   "outputs": [],
+   "source": [
+    "import torchaudio\n",
+    "\n",
+    "def speech_file_to_array_fn(batch):\n",
+    "    speech_array, sampling_rate = torchaudio.load(batch[\"path\"])\n",
+    "    batch[\"speech\"] = speech_array[0].numpy()\n",
+    "    batch[\"sampling_rate\"] = sampling_rate\n",
+    "    batch[\"target_text\"] = batch[\"sentence\"]\n",
+    "    return batch"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# common_voice_train_array = common_voice_train.map(speech_file_to_array_fn, remove_columns=common_voice_train.column_names)\n",
+    "# common_voice_test_array = common_voice_test.map(speech_file_to_array_fn, remove_columns=common_voice_test.column_names)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Loud Normalisation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import soundfile as sf\n",
+    "import pyloudnorm as pyln\n",
+    "\n",
+    "def get_loudness_normalised(sa, sr):\n",
+    "    # peak normalize audio to -1 dB\n",
+    "    peak_normalized_audio = pyln.normalize.peak(sa, -1.0)\n",
+    "\n",
+    "    # measure the loudness first \n",
+    "    meter = pyln.Meter(sr) # create BS.1770 meter\n",
+    "    loudness = meter.integrated_loudness(sa)\n",
+    "\n",
+    "    # loudness normalize audio to -12 dB LUFS\n",
+    "    loudness_normalized_audio = pyln.normalize.loudness(sa, loudness, -12.0)\n",
+    "\n",
+    "    return loudness_normalized_audio"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def speech_file_to_array_loud_norm_fn(batch):\n",
+    "    speech_array, sampling_rate = torchaudio.load(batch[\"path\"])\n",
+    "#     print('batch all',batch) # just to see which one is causing exceptions\n",
+    "    \n",
+    "    # DO loudness normalisation\n",
+    "    sa = get_loudness_normalised(speech_array[0].numpy(), sampling_rate)\n",
+    "    \n",
+    "    batch[\"speech\"] = sa\n",
+    "    batch[\"sampling_rate\"] = sampling_rate\n",
+    "    batch[\"target_text\"] = batch[\"sentence\"]\n",
+    "    return batch"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Only normalise Train set"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "({'path': '/home/tyoc213/.cache/huggingface/datasets/downloads/extracted/27bd561157b7c36fa5c2e7638cb225ed76cb912aa0c4727171bcc12570c16c1c/cv-corpus-6.1-2020-12-11/de/clips/common_voice_de_21623135.mp3',\n",
+       "  'sentence': 'darüber besteht überall klarheit '},\n",
+       " {'path': 'nahuatl_slr90_by_sentence/28_85.flac',\n",
+       "  'sentence': 'de se: kiteki ihkó:n '})"
+      ]
+     },
+     "execution_count": 43,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "common_voice_train[99],common_voice_train[100],"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 44,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 117,
+     "referenced_widgets": [
+      "348ef54c80b2449f8a3bc950cccd62cc",
+      "b78413dcc0584a0c8f71731a06aaa1b8",
+      "7edbecaccdd94ede8fddc0e1807e777e",
+      "5e3aad95e52f4be2bd670d1345398f1b",
+      "b9c5c6dd54cc4dc5ad5a2bb69a24ab05",
+      "3e3a022a9f304b0f9f7ef067fcee1e56",
+      "7aa70322bdfe46938b583a20003093d5",
+      "99d5c44ea54b45ee9bd89380cb1ad189",
+      "5f48f54986924e418aa4ac22aa54b714",
+      "db71db50799c404aafa4a54de8b9b799",
+      "a58c203a7cc54086aea45f2029821207",
+      "8d409ca0372a48e2972ca1d8eee5ffa1",
+      "c8fdf261ac294093a355778a3a4aba3b",
+      "b1b6a4649fc34c9996f993c57671766b",
+      "d362345c05234c97a675c6bacdad0e92",
+      "b0479f03f96241ca959f6fe7bcbd1aba"
+     ]
+    },
+    "id": "afeicUeWlrRL",
+    "outputId": "d5e4d41a-61d6-4094-eba9-a5bbed02cedc"
+   },
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "099bf3d9f18c41318e1d3631a90a4c56",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "HBox(children=(FloatProgress(value=0.0, max=600.0), HTML(value='')))"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "CPU times: user 8.77 s, sys: 1.63 s, total: 10.4 s\n",
+      "Wall time: 10.9 s\n"
+     ]
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "##### nahuatl no normalization of loudness\n",
+    "#common_voice_train = common_voice_train.map(speech_file_to_array_loud_norm_fn, num_proc=2)\n",
+    "common_voice_train = common_voice_train.map(speech_file_to_array_fn)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 45,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "655637121a8348968d50d9ab2d40c1cc",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "HBox(children=(FloatProgress(value=0.0), HTML(value='')))"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "CPU times: user 1.33 s, sys: 185 ms, total: 1.52 s\n",
+      "Wall time: 1.52 s\n"
+     ]
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "common_voice_test = common_voice_test.map(speech_file_to_array_fn)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "ki5sXmzucc9Q"
+   },
+   "source": [
+    "Great, now we've successfully read in all the audio files, but since we know that Common Voice is sampled at 48kHz, we need to resample the audio files to 16kHz. \n",
+    "\n",
+    "Let's make use of the [`librosa`](https://github.com/librosa/librosa) library to downsample the data."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 46,
+   "metadata": {
+    "id": "6Y6AK3Z-kHwP"
+   },
+   "outputs": [],
+   "source": [
+    "import librosa\n",
+    "import numpy as np\n",
+    "\n",
+    "def resample(batch):\n",
+    "#     print(len(batch['speech']), type(batch['speech']))\n",
+    "#     print(batch['path'])\n",
+    "#     print(batch['target_text'])\n",
+    "    # nahuatl note: make nans zero!!!! (that is correct?)\n",
+    "    arr = np.asarray(batch[\"speech\"])\n",
+    "    arr[np.isnan(arr)] = 0\n",
+    "    batch[\"speech\"] = librosa.resample(arr, 48_000, 16_000)\n",
+    "    batch[\"sampling_rate\"] = 16_000\n",
+    "    return batch"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 47,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 453,
+     "referenced_widgets": [
+      "ee641bbf54a7499597713c517baa81bb",
+      "3d929b9e2518402b81a71757ffb753d2",
+      "4f8957dc035d4c1a9e8630fc8ab8cd10",
+      "757e7bd0e6c5410da0490d191b4e68c8",
+      "596aea0362924c7db583203268dd5a3e",
+      "47a6c3c427614f21a6dab1c048e5dd37",
+      "0b795d4b68014de19bf9579c67b55ffb",
+      "9185f86719af476da41e3835e8f06f8d",
+      "771959e46cb64b3ebafe931f96f5ff52",
+      "0e999af234bd4b63ad2937e61d08b693",
+      "f792530a76ee486688cbc2502dfae594",
+      "d69468d63dd74fdd807fe061b92aa84e",
+      "1261590ef796493798f7068ea0547b74",
+      "7e50f8027fb74d669daae5e46082026c",
+      "7f5203fde6b64bf7ad53d6ecd3041bfc",
+      "84e7f0001ebe458dad3c96e7e9a38cdc",
+      "24ea17ae8ab14e8a871e5e115c3f4c06",
+      "f57d087016124ebeb073fd7428dcb68b",
+      "f3905820a42c499fba04af9c1ad19705",
+      "4e1a725fd90b45e280b8b0028ba65250",
+      "4c0ad31e73234e46aac0a297ec18bdeb",
+      "fc9504846f424542a7feb932964f1f5b",
+      "9f79629ad6a94201acf3283862d1ae17",
+      "491fd969d61a478f8e85ffcd3e1a3e20",
+      "76d162d3ea0845cc837651a77a5a2d36",
+      "98c594f1e41e4b3fab10f0763bd93d75",
+      "f6b01ad0433a40178ef3ba5657bc1583",
+      "eed2ccc12daa4c71b080794a7a18f5cb",
+      "beca070c32124a119a08cb21c2ca95e5",
+      "69828f4a101f4340916a4be141866904",
+      "20347ed29fdc4c0a96da28c09aacf44d",
+      "f18eddbd3d994ddc88f37e02d754c206",
+      "b7c43fb5efdd4afbb82c81b923f2815a",
+      "c0a661f20e7e4649a3c8c42a5fd01956",
+      "8dddd0245dcb4532917cbfa0181d2a00",
+      "3bdb4058f40f40e3a10e323325a64638",
+      "024989cea06f435894776b0a921164b2",
+      "b1d93a7521fa47b8a815445b5232da59",
+      "751ae6b9e2da4b85be9600561485f1ac",
+      "d7f27e9cf8a844349ca90393e0c49a03",
+      "82015055d32449b89346ea18e7474c4d",
+      "a170c0cb21cf425fbee97fd6d5584e2c",
+      "f5f1f0865d7e4d8b810ccb9c3c4d2683",
+      "416badb151ee4660b53fdbc136e0c8fb",
+      "a47f1ea64f894f0b8e6b277c31ae9f7d",
+      "e51b5fd9d5a6416d986fac1526d1666f",
+      "824569c63ec445c08362659ca228dd2a",
+      "0f3756509e3b405d87936f599b153de2",
+      "d96e01ad62c342cdb7d9b1eceb39afa3",
+      "e6ce9330460d4a0fb67cc493ca74ae96",
+      "e6178f7b148c4bf39f2826f208e0cc64",
+      "f78ff14b9c8f46448ed1ecb3fe1f5e0b",
+      "929cde17b3484f3e9e8f8774bc43e374",
+      "6ba6d07674a34836be53cf173c2b61ca",
+      "5a5bc8b4a1c644dea08a60128d888d10",
+      "b054b00a32e64fc5988fbd2966ebbce6",
+      "5ccd12253fff448f9c15c9b03c70a408",
+      "330226a977694de1bd88c0aa3789be47",
+      "f203c54e7e054d97aa4d1097f320f611",
+      "6266a4019e124aff877bb55f21740180",
+      "3ec3285e9f3e4a5abcefabb7f140f4a3",
+      "0cd1932178c945d48604ffd299e65d2c",
+      "8ad3e4b211e34c048d0f48e36fdbfe48",
+      "55071fc1b7484620803aeba453e9af72"
+     ]
+    },
+    "id": "Ws8DyIL_kjwT",
+    "outputId": "6176aea2-5986-4da0-a2ad-6ef5e2c85493"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "CPU times: user 1.89 s, sys: 2.61 s, total: 4.5 s\n",
+      "Wall time: 35.2 s\n"
+     ]
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "common_voice_train = common_voice_train.map(resample, num_proc=4)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 48,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "CPU times: user 356 ms, sys: 430 ms, total: 787 ms\n",
+      "Wall time: 5.76 s\n"
+     ]
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "common_voice_test = common_voice_test.map(resample, num_proc=4)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 49,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "ok\n"
+     ]
+    }
+   ],
+   "source": [
+    "print('ok')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "SOckzFd4Mbzq"
+   },
+   "source": [
+    "This seemed to have worked! Let's listen to a couple of audio files to better understand the dataset and verify that the audio was correctly loaded. \n",
+    "\n",
+    "**Note**: *You can click the following cell a couple of times to listen to different speech samples.*"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 50,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 74
+    },
+    "id": "dueM6U7Ev0OA",
+    "outputId": "1a3e579d-213e-4c7a-b2ec-9a7725d95afc"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "\n",
+       "                <audio  controls=\"controls\" autoplay=\"autoplay\">\n",
+       "                    <source src=\"data:audio/wav;base64,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\" type=\"audio/wav\" />\n",
+       "                    Your browser does not support the audio element.\n",
+       "                </audio>\n",
+       "              "
+      ],
+      "text/plain": [
+       "<IPython.lib.display.Audio object>"
+      ]
+     },
+     "execution_count": 50,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import IPython.display as ipd\n",
+    "import numpy as np\n",
+    "import random\n",
+    "\n",
+    "rand_int = random.randint(0, len(common_voice_train)-1)\n",
+    "\n",
+    "ipd.Audio(data=np.asarray(common_voice_train[rand_int][\"speech\"]), autoplay=True, rate=16000)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 51,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'nahuatl_slr90_by_sentence/5_78.flac'"
+      ]
+     },
+     "execution_count": 51,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "common_voice_train[rand_int][\"path\"]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "1MaL9J2dNVtG"
+   },
+   "source": [
+    "It can be heard, that the speakers change along with their speaking rate, accent, and background environment, etc. Overall, the recordings sound acceptably clear though, which is to be expected from a crowd-sourced read speech corpus.\n",
+    "\n",
+    "Let's do a final check that the data is correctly prepared, by printing the shape of the speech input, its transcription, and the corresponding sampling rate.\n",
+    "\n",
+    "**Note**: *You can click the following cell a couple of times to verify multiple samples.*"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 52,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "1Po2g7YPuRTx",
+    "outputId": "96b0b82c-a5df-4ae6-d17b-9c7d4f710b42"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Target text: duró diez años en el trono \n",
+      "Input array shape: (53376,)\n",
+      "Sampling rate: 16000\n"
+     ]
+    }
+   ],
+   "source": [
+    "rand_int = random.randint(0, len(common_voice_train)-1)\n",
+    "\n",
+    "print(\"Target text:\", common_voice_train[rand_int][\"target_text\"])\n",
+    "print(\"Input array shape:\", np.asarray(common_voice_train[rand_int][\"speech\"]).shape)\n",
+    "print(\"Sampling rate:\", common_voice_train[rand_int][\"sampling_rate\"])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "M9teZcSwOBJ4"
+   },
+   "source": [
+    "Good! Everything looks fine - the data is a 1-dimensional array, the sampling rate always corresponds to 16kHz, and the target text is normalized."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "k3Pbn5WvOYZF"
+   },
+   "source": [
+    "Finally, we can process the dataset to the format expected by the model for training. We will again make use of the `map(...)` function.\n",
+    "\n",
+    "First, we check that the data samples have the same sampling rate of 16kHz.\n",
+    "Second, we extract the `input_values` from the loaded audio file. In our case, this includes only normalization, but for other speech models, this step could correspond to extracting, *e.g.* [Log-Mel features](https://en.wikipedia.org/wiki/Mel-frequency_cepstrum). \n",
+    "Third, we encode the transcriptions to label ids.\n",
+    "\n",
+    "**Note**: This mapping function is a good example of how the `Wav2Vec2Processor` class should be used. In \"normal\" context, calling `processor(...)` is redirected to `Wav2Vec2FeatureExtractor`'s call method. When wrapping the processor into the `as_target_processor` context, however, the same method is redirected to `Wav2Vec2CTCTokenizer`'s call method.\n",
+    "For more information please check the [docs](https://huggingface.co/transformers/master/model_doc/wav2vec2.html#transformers.Wav2Vec2Processor.__call__)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 53,
+   "metadata": {
+    "id": "eJY7I0XAwe9p"
+   },
+   "outputs": [],
+   "source": [
+    "def prepare_dataset(batch):\n",
+    "    # check that all files have the correct sampling rate\n",
+    "    assert (\n",
+    "        len(set(batch[\"sampling_rate\"])) == 1\n",
+    "    ), f\"Make sure all inputs have the same sampling rate of {processor.feature_extractor.sampling_rate}.\"\n",
+    "\n",
+    "    batch[\"input_values\"] = processor(batch[\"speech\"], sampling_rate=batch[\"sampling_rate\"][0]).input_values\n",
+    "    \n",
+    "    with processor.as_target_processor():\n",
+    "        batch[\"labels\"] = processor(batch[\"target_text\"]).input_ids\n",
+    "    return batch"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 54,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 509,
+     "referenced_widgets": [
+      "4797f1acd9924b4e97f12f964c83078c",
+      "73940df84ffd4e0f96637342e9fd12b7",
+      "5370c0f2d54b45c0a89f11fb5b70cd4b",
+      "018c1f8e198e4df4b480e609bd1be602",
+      "fa7926bbe77e48b3a0648b45f5d2dc7a",
+      "020bdb330b0d40f5b89697ff37025f69",
+      "d35c15beeb33476894b07c3563f8facd",
+      "768ab09956774f50a79b2493a8bf179b",
+      "7ef969e47c2d429a9848d5ab3f5bb2d9",
+      "fe62265afdc74026b7e9c5a50ef61d2c",
+      "015c5690e1ea4281954c7efda1c80a6a",
+      "f4135dd72864445391f43f387635bfdc",
+      "2f727c76652944e3892dd584bea11af2",
+      "dec796237765477ea904834d9a824b61",
+      "8df9d19602cb4951b397c385458a11ef",
+      "923ed9e127524187ab8cfcac31164ba7",
+      "bf9e57d81135412d9a9a2281f28bd52a",
+      "c41610c0baef412984f8661d96e08b7e",
+      "579b6055028f473981ce789a0733a753",
+      "4fb7347e9ca542e6ab9003bf4db218e0",
+      "3133b378b9294a759c8dfb786ed8f815",
+      "6de66d6b7a73434cbdc59b2109bdf0a0",
+      "6d4a26d876fb4ac6b5948a09945bdc6b",
+      "0987aac282af415da2fbc9dc1b4d5069",
+      "ac35dca0845149a284b9867d9e607232",
+      "b54bff6261964119bcb562c1a9f74ce6",
+      "5071a31d06f544a5b7340a4e863d8fdf",
+      "542027ba12f444d586e8072452badea0",
+      "49defa4284554baf85f32de242b22709",
+      "b2473405490e4556bf30c0cc81237aa5",
+      "02bdb06c176145feaa842b97ae58609c",
+      "bc41384bbae04044b9780651c6b5a47c",
+      "7040945accce4739a41746cc75bb7fce",
+      "71011f0d2bc942ac8f9ea1d1fd30c78d",
+      "6f60626242534f44a6381195e6eb6530",
+      "9fee9d9dd1164d97a9109e942444c332",
+      "5ab30242cd154ec0b560c23c0f178546",
+      "0ffcbedb8d4444508ac0c3c0b41ea8ac",
+      "f9efaa7678c2450f847ff2c2f21ff96e",
+      "c126ea97019149848396e593cfab016f",
+      "0f99011a13754ed99f3c51a478b0e793",
+      "4abe2731ec624729b401d60a392cae63",
+      "bd187486ac2548f2961cfcb63d852de1",
+      "3f780f0aa8834fc189b292e0474e2ffa",
+      "231c66f195d34f86b216805518f4bccd",
+      "58f3e8002f984594ac05c973aa78ef69",
+      "ec36a94ee2574ac8b227ccaefdee5520",
+      "a868dea9d9b047a4b853b390e138e4c1",
+      "6462bd9561e24abb98fce6ce4675d810",
+      "bd3447291ce54812af10ac6245ea4328",
+      "e273548a15aa4d4994132b317adb66fc",
+      "f6930dd5519d4dfda64c597def220a30",
+      "7d62810674c8482abe46c60fc08884b4",
+      "80697300a4394b909f1c499ba80aeb13",
+      "ab72c80dfd5e4ab19a183f4204486b59",
+      "56ad6231a0a04228be29ceecbc6b7c0e",
+      "b6221b4c04e64c9da9eb9e11539bac89",
+      "dc6862530f6e429ba61a169b4c95722c",
+      "02d1f77324854fbca0df9384c57faac8",
+      "8e63ba7f1fd24555bf11bc9dbe9c770b",
+      "704ea5e05fd744d998b76d6435992995",
+      "d4a3f79644fc41848450ba29e6fdfc3d",
+      "405b5de4ae854cf9896f63d15f2207dd",
+      "26e7bab0f3bf4797bfcef83dcace24f0"
+     ]
+    },
+    "id": "-np9xYK-wl8q",
+    "outputId": "6155b5f0-a5a2-4e20-d0e2-0b3a60c13f98"
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/tyoc213/miniconda3/envs/fastai/lib/python3.8/site-packages/numpy/core/_asarray.py:83: VisibleDeprecationWarning: Creating an ndarray from ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated. If you meant to do this, you must specify 'dtype=object' when creating the ndarray\n",
+      "  return array(a, dtype, copy=False, order=order)\n",
+      "/home/tyoc213/miniconda3/envs/fastai/lib/python3.8/site-packages/numpy/core/_asarray.py:83: VisibleDeprecationWarning: Creating an ndarray from ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated. If you meant to do this, you must specify 'dtype=object' when creating the ndarray\n",
+      "  return array(a, dtype, copy=False, order=order)\n",
+      "/home/tyoc213/miniconda3/envs/fastai/lib/python3.8/site-packages/numpy/core/_asarray.py:83: VisibleDeprecationWarning: Creating an ndarray from ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated. If you meant to do this, you must specify 'dtype=object' when creating the ndarray\n",
+      "  return array(a, dtype, copy=False, order=order)\n",
+      "/home/tyoc213/miniconda3/envs/fastai/lib/python3.8/site-packages/numpy/core/_asarray.py:83: VisibleDeprecationWarning: Creating an ndarray from ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated. If you meant to do this, you must specify 'dtype=object' when creating the ndarray\n",
+      "  return array(a, dtype, copy=False, order=order)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/tyoc213/miniconda3/envs/fastai/lib/python3.8/site-packages/numpy/core/_asarray.py:83: VisibleDeprecationWarning: Creating an ndarray from ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated. If you meant to do this, you must specify 'dtype=object' when creating the ndarray\n",
+      "  return array(a, dtype, copy=False, order=order)\n",
+      "/home/tyoc213/miniconda3/envs/fastai/lib/python3.8/site-packages/numpy/core/_asarray.py:83: VisibleDeprecationWarning: Creating an ndarray from ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated. If you meant to do this, you must specify 'dtype=object' when creating the ndarray\n",
+      "  return array(a, dtype, copy=False, order=order)\n",
+      "/home/tyoc213/miniconda3/envs/fastai/lib/python3.8/site-packages/numpy/core/_asarray.py:83: VisibleDeprecationWarning: Creating an ndarray from ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated. If you meant to do this, you must specify 'dtype=object' when creating the ndarray\n",
+      "  return array(a, dtype, copy=False, order=order)\n",
+      "/home/tyoc213/miniconda3/envs/fastai/lib/python3.8/site-packages/numpy/core/_asarray.py:83: VisibleDeprecationWarning: Creating an ndarray from ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated. If you meant to do this, you must specify 'dtype=object' when creating the ndarray\n",
+      "  return array(a, dtype, copy=False, order=order)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "common_voice_train = common_voice_train.map(prepare_dataset, remove_columns=common_voice_train.column_names, batch_size=8, num_proc=4, batched=True)\n",
+    "common_voice_test = common_voice_test.map(prepare_dataset, remove_columns=common_voice_test.column_names, batch_size=8, num_proc=4, batched=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "gYlQkKVoRUos"
+   },
+   "source": [
+    "## Training\n",
+    "\n",
+    "The data is processed so that we are ready to start setting up the training pipeline. We will make use of 🤗's [Trainer](https://huggingface.co/transformers/master/main_classes/trainer.html?highlight=trainer) for which we essentially need to do the following:\n",
+    "\n",
+    "- Define a data collator. In contrast to most NLP models, XLSR-Wav2Vec2 has a much larger input length than output length. *E.g.*, a sample of input length 50000 has an output length of no more than 100. Given the large input sizes, it is much more efficient to pad the training batches dynamically meaning that all training samples should only be padded to the longest sample in their batch and not the overall longest sample. Therefore, fine-tuning XLSR-Wav2Vec2 requires a special padding data collator, which we will define below\n",
+    "\n",
+    "- Evaluation metric. During training, the model should be evaluated on the word error rate. We should define a `compute_metrics` function accordingly\n",
+    "\n",
+    "- Load a pretrained checkpoint. We need to load a pretrained checkpoint and configure it correctly for training.\n",
+    "\n",
+    "- Define the training configuration.\n",
+    "\n",
+    "After having fine-tuned the model, we will correctly evaluate it on the test data and verify that it has indeed learned to correctly transcribe speech."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "Slk403unUS91"
+   },
+   "source": [
+    "### Set-up Trainer\n",
+    "\n",
+    "Let's start by defining the data collator. The code for the data collator was copied from [this example](https://github.com/huggingface/transformers/blob/9a06b6b11bdfc42eea08fa91d0c737d1863c99e3/examples/research_projects/wav2vec2/run_asr.py#L81).\n",
+    "\n",
+    "Without going into too many details, in contrast to the common data collators, this data collator treats the `input_values` and `labels` differently and thus applies to separate padding functions on them (again making use of XLSR-Wav2Vec2's context manager). This is necessary because in speech input and output are of different modalities meaning that they should not be treated by the same padding function.\n",
+    "Analogous to the common data collators, the padding tokens in the labels with `-100` so that those tokens are **not** taken into account when computing the loss."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 55,
+   "metadata": {
+    "id": "tborvC9hx88e"
+   },
+   "outputs": [],
+   "source": [
+    "import torch\n",
+    "\n",
+    "from dataclasses import dataclass, field\n",
+    "from typing import Any, Dict, List, Optional, Union\n",
+    "\n",
+    "@dataclass\n",
+    "class DataCollatorCTCWithPadding:\n",
+    "    \"\"\"\n",
+    "    Data collator that will dynamically pad the inputs received.\n",
+    "    Args:\n",
+    "        processor (:class:`~transformers.Wav2Vec2Processor`)\n",
+    "            The processor used for proccessing the data.\n",
+    "        padding (:obj:`bool`, :obj:`str` or :class:`~transformers.tokenization_utils_base.PaddingStrategy`, `optional`, defaults to :obj:`True`):\n",
+    "            Select a strategy to pad the returned sequences (according to the model's padding side and padding index)\n",
+    "            among:\n",
+    "            * :obj:`True` or :obj:`'longest'`: Pad to the longest sequence in the batch (or no padding if only a single\n",
+    "              sequence if provided).\n",
+    "            * :obj:`'max_length'`: Pad to a maximum length specified with the argument :obj:`max_length` or to the\n",
+    "              maximum acceptable input length for the model if that argument is not provided.\n",
+    "            * :obj:`False` or :obj:`'do_not_pad'` (default): No padding (i.e., can output a batch with sequences of\n",
+    "              different lengths).\n",
+    "        max_length (:obj:`int`, `optional`):\n",
+    "            Maximum length of the ``input_values`` of the returned list and optionally padding length (see above).\n",
+    "        max_length_labels (:obj:`int`, `optional`):\n",
+    "            Maximum length of the ``labels`` returned list and optionally padding length (see above).\n",
+    "        pad_to_multiple_of (:obj:`int`, `optional`):\n",
+    "            If set will pad the sequence to a multiple of the provided value.\n",
+    "            This is especially useful to enable the use of Tensor Cores on NVIDIA hardware with compute capability >=\n",
+    "            7.5 (Volta).\n",
+    "    \"\"\"\n",
+    "\n",
+    "    processor: Wav2Vec2Processor\n",
+    "    padding: Union[bool, str] = True\n",
+    "    max_length: Optional[int] = None\n",
+    "    max_length_labels: Optional[int] = None\n",
+    "    pad_to_multiple_of: Optional[int] = None\n",
+    "    pad_to_multiple_of_labels: Optional[int] = None\n",
+    "\n",
+    "    def __call__(self, features: List[Dict[str, Union[List[int], torch.Tensor]]]) -> Dict[str, torch.Tensor]:\n",
+    "        # split inputs and labels since they have to be of different lenghts and need\n",
+    "        # different padding methods\n",
+    "        input_features = [{\"input_values\": feature[\"input_values\"]} for feature in features]\n",
+    "        label_features = [{\"input_ids\": feature[\"labels\"]} for feature in features]\n",
+    "\n",
+    "        batch = self.processor.pad(\n",
+    "            input_features,\n",
+    "            padding=self.padding,\n",
+    "            max_length=self.max_length,\n",
+    "            pad_to_multiple_of=self.pad_to_multiple_of,\n",
+    "            return_tensors=\"pt\",\n",
+    "        )\n",
+    "        with self.processor.as_target_processor():\n",
+    "            labels_batch = self.processor.pad(\n",
+    "                label_features,\n",
+    "                padding=self.padding,\n",
+    "                max_length=self.max_length_labels,\n",
+    "                pad_to_multiple_of=self.pad_to_multiple_of_labels,\n",
+    "                return_tensors=\"pt\",\n",
+    "            )\n",
+    "\n",
+    "        # replace padding with -100 to ignore loss correctly\n",
+    "        labels = labels_batch[\"input_ids\"].masked_fill(labels_batch.attention_mask.ne(1), -100)\n",
+    "\n",
+    "        batch[\"labels\"] = labels\n",
+    "\n",
+    "        return batch"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 56,
+   "metadata": {
+    "id": "lbQf5GuZyQ4_"
+   },
+   "outputs": [],
+   "source": [
+    "data_collator = DataCollatorCTCWithPadding(processor=processor, padding=True,\n",
+    "                                          pad_to_multiple_of=8, pad_to_multiple_of_labels=8)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "xO-Zdj-5cxXp"
+   },
+   "source": [
+    "Next, the evaluation metric is defined. As mentioned earlier, the \n",
+    "predominant metric in ASR is the word error rate (WER), hence we will use it in this notebook as well."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 57,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 67,
+     "referenced_widgets": [
+      "d5fb02debe4347e781543a996ce39be3",
+      "da12267c52144292adb9896249d61a6a",
+      "8e1a85a4a6214a16b7431da23a301ada",
+      "57198e3250374e1fa64c5a4be255861e",
+      "a3c04c75ec9743feb795f69e7c4dff4f",
+      "d453bd4a35e54bfba20dac1fe86c60c1",
+      "969080b52ad44ee997829986d198c505",
+      "8f737725708c4097a8caaf4da6229636"
+     ]
+    },
+    "id": "9Xsux2gmyXso",
+    "outputId": "58e0e6f5-6131-4147-bccb-6c42223833db"
+   },
+   "outputs": [],
+   "source": [
+    "wer_metric = load_metric(\"wer\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "E1qZU5p-deqB"
+   },
+   "source": [
+    "The model will return a sequence of logit vectors:\n",
+    "$\\mathbf{y}_1, \\ldots, \\mathbf{y}_m$ with $\\mathbf{y}_1 = f_{\\theta}(x_1, \\ldots, x_n)[0]$ and $n >> m$.\n",
+    "\n",
+    "A logit vector $\\mathbf{y}_1$ contains the log-odds for each word in the vocabulary we defined earlier, thus $\\text{len}(\\mathbf{y}_i) =$ `config.vocab_size`. We are interested in the most likely prediction of the model and thus take the `argmax(...)` of the logits. Also, we transform the encoded labels back to the original string by replacing `-100` with the `pad_token_id` and decoding the ids while making sure that consecutive tokens are **not** grouped to the same token in CTC style ${}^1$."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 58,
+   "metadata": {
+    "id": "1XZ-kjweyTy_"
+   },
+   "outputs": [],
+   "source": [
+    "def compute_metrics(pred):\n",
+    "    pred_logits = pred.predictions\n",
+    "    pred_ids = np.argmax(pred_logits, axis=-1)\n",
+    "\n",
+    "    pred.label_ids[pred.label_ids == -100] = processor.tokenizer.pad_token_id\n",
+    "\n",
+    "    pred_str = processor.batch_decode(pred_ids)\n",
+    "    # we do not want to group tokens when computing the metrics\n",
+    "    label_str = processor.batch_decode(pred.label_ids, group_tokens=False)\n",
+    "\n",
+    "    wer = wer_metric.compute(predictions=pred_str, references=label_str)\n",
+    "\n",
+    "    return {\"wer\": wer}"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "Xmgrx4bRwLIH"
+   },
+   "source": [
+    "Now, we can load the pretrained `XLSR-Wav2Vec2` checkpoint. The tokenizer's `pad_token_id` must be to define the model's `pad_token_id` or in the case of `Wav2Vec2ForCTC` also CTC's *blank token* ${}^2$. To save GPU memory, we enable PyTorch's [gradient checkpointing](https://pytorch.org/docs/stable/checkpoint.html) and also set the loss reduction to \"*mean*\".\n",
+    "\n",
+    "Because the dataset is quite small (~6h of training data) and because Common Voice is quite noisy, fine-tuning Facebook's [wav2vec2-large-xlsr-53 checkpoint](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) seems to require some hyper-parameter tuning. Therefore, I had to play around a bit with different values for dropout, [SpecAugment](https://arxiv.org/abs/1904.08779)'s masking dropout rate, layer dropout, and the learning rate until training seemed to be stable enough. \n",
+    "\n",
+    "**Note**: When using this notebook to train XLSR-Wav2Vec2 on another language of Common Voice those hyper-parameter settings might not work very well. Feel free to adapt those depending on your use case. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 59,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "e7cqAWIayn6w",
+    "outputId": "0a5ab559-6c38-47c6-b4f5-64480ed1df65"
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Some weights of Wav2Vec2ForCTC were not initialized from the model checkpoint at facebook/wav2vec2-large-xlsr-53 and are newly initialized: ['lm_head.bias', 'lm_head.weight']\n",
+      "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
+     ]
+    }
+   ],
+   "source": [
+    "from transformers import Wav2Vec2ForCTC\n",
+    "\n",
+    "model = Wav2Vec2ForCTC.from_pretrained(\n",
+    "    \"facebook/wav2vec2-large-xlsr-53\", \n",
+    "    attention_dropout=0.1,\n",
+    "    hidden_dropout=0.1,\n",
+    "    feat_proj_dropout=0.0,\n",
+    "    mask_time_prob=0.05,\n",
+    "    layerdrop=0.1,\n",
+    "    gradient_checkpointing=True, \n",
+    "    ctc_loss_reduction=\"mean\", \n",
+    "    pad_token_id=processor.tokenizer.pad_token_id,\n",
+    "    vocab_size=len(processor.tokenizer)\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "1DwR3XLSzGDD"
+   },
+   "source": [
+    "The first component of XLSR-Wav2Vec2 consists of a stack of CNN layers that are used to extract acoustically meaningful - but contextually independent - features from the raw speech signal. This part of the model has already been sufficiently trained during pretraining and as stated in the [paper](https://arxiv.org/pdf/2006.13979.pdf) does not need to be fine-tuned anymore. \n",
+    "Thus, we can set the `requires_grad` to `False` for all parameters of the *feature extraction* part."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 60,
+   "metadata": {
+    "id": "oGI8zObtZ3V0"
+   },
+   "outputs": [],
+   "source": [
+    "model.freeze_feature_extractor()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "lD4aGhQM0K-D"
+   },
+   "source": [
+    "In a final step, we define all parameters related to training. \n",
+    "To give more explanation on some of the parameters:\n",
+    "- `group_by_length` makes training more efficient by grouping training samples of similar input length into one batch. This can significantly speed up training time by heavily reducing the overall number of useless padding tokens that are passed through the model\n",
+    "- `learning_rate` and `weight_decay` were heuristically tuned until fine-tuning has become stable. Note that those parameters strongly depend on the Common Voice dataset and might be suboptimal for other speech datasets.\n",
+    "\n",
+    "For more explanations on other parameters, one can take a look at the [docs](https://huggingface.co/transformers/master/main_classes/trainer.html?highlight=trainer#trainingarguments).\n",
+    "\n",
+    "**Note**: If one wants to save the trained models in his/her google drive the commented-out `output_dir` can be used instead."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Here starts the first training\n",
+    "\n",
+    "\n",
+    "# Here starts the first training"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 61,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from transformers import TrainingArguments\n",
+    "\n",
+    "training_args = TrainingArguments(\n",
+    "  output_dir=the_name('-one'),\n",
+    "  # output_dir=\"./wav2vec2-large-xlsr-nahuatl-demo\",\n",
+    "  group_by_length=True,\n",
+    "  per_device_train_batch_size=32,\n",
+    "  per_device_eval_batch_size=64,\n",
+    "  gradient_accumulation_steps=1,\n",
+    "  evaluation_strategy=\"steps\",\n",
+    "  num_train_epochs=150,\n",
+    "  fp16=True,\n",
+    "  save_steps=25,\n",
+    "  eval_steps=25,\n",
+    "  logging_steps=5,\n",
+    "  learning_rate=3e-4,\n",
+    "  warmup_steps=200,\n",
+    "  save_total_limit=1,\n",
+    "    \n",
+    "  # WANDB LOGGING: \n",
+    "  report_to = 'wandb',  # enable logging to W&B\n",
+    "  run_name = the_name('-one')+'-ie-base-50e-ovh-4-4-upgrade',   # Name your run, optional\n",
+    "  load_best_model_at_end = True,  # This will ensure your best model will be uploaded to W&B\n",
+    "  metric_for_best_model='wer',    # Load best model based on \"wer\", not eval loss\n",
+    "  greater_is_better=False,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "OsW-WZcL1ZtN"
+   },
+   "source": [
+    "Now, all instances can be passed to Trainer and we are ready to start training!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 62,
+   "metadata": {
+    "id": "rY7vBmFCPFgC"
+   },
+   "outputs": [],
+   "source": [
+    "from transformers import Trainer\n",
+    "\n",
+    "trainer = Trainer(\n",
+    "    model=model,\n",
+    "    data_collator=data_collator,\n",
+    "    args=training_args,\n",
+    "    compute_metrics=compute_metrics,\n",
+    "    train_dataset=common_voice_train,\n",
+    "    eval_dataset=common_voice_test,\n",
+    "    tokenizer=processor.feature_extractor,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "UoXBx1JAA0DX"
+   },
+   "source": [
+    "\n",
+    "\n",
+    "---\n",
+    "\n",
+    "${}^1$ To allow models to become independent of the speaker rate, in CTC, consecutive tokens that are identical are simply grouped as a single token. However, the encoded labels should not be grouped when decoding since they don't correspond to the predicted tokens of the model, which is why the `group_tokens=False` parameter has to be passed. If we wouldn't pass this parameter a word like `\"hello\"` would incorrectly be encoded, and decoded as `\"helo\"`.\n",
+    "\n",
+    "${}^2$ The blank token allows the model to predict a word, such as `\"hello\"` by forcing it to insert the blank token between the two l's. A CTC-conform prediction of `\"hello\"` of our model would be `[PAD] [PAD] \"h\" \"e\" \"e\" \"l\" \"l\" [PAD] \"l\" \"o\" \"o\" [PAD]`."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "rpvZHM1xReIW"
+   },
+   "source": [
+    "### Training"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "j-3oKSzZ1hGq"
+   },
+   "source": [
+    "Training will take between 180 and 240 minutes depending on the GPU allocated to this notebook. While the trained model yields somewhat satisfying results on *Common Voice*'s test data of Turkish, it is by no means an optimally fine-tuned model. The purpose of this notebook is to demonstrate how XLSR-Wav2Vec2's [checkpoint](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) can be fine-tuned on a low-resource ASR dataset.\n",
+    "\n",
+    "In case you want to use this google colab to fine-tune your model, you should make sure that your training doesn't stop due to inactivity. A simple hack to prevent this is to paste the following code into the console of this tab (*right mouse click -> inspect -> Console tab and insert code*)."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "VYYAvgkW4P0m"
+   },
+   "source": [
+    "```javascript\n",
+    "function ConnectButton(){\n",
+    "    console.log(\"Connect pushed\"); \n",
+    "    document.querySelector(\"#top-toolbar > colab-connect-button\").shadowRoot.querySelector(\"#connect\").click() \n",
+    "}\n",
+    "setInterval(ConnectButton,60000);\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 63,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 348
+    },
+    "id": "_UEjJqGsQw24",
+    "outputId": "2e23b190-ca76-48ad-8117-376d1d7c058e"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "\n",
+       "                Tracking run with wandb version 0.10.23<br/>\n",
+       "                Syncing run <strong style=\"color:#cdcd00\">final0-wav2vec2-large-xlsr-nahuatl-es-de--one-ie-base-50e-ovh-4-4-upgrade</strong> to <a href=\"https://wandb.ai\" target=\"_blank\">Weights & Biases</a> <a href=\"https://docs.wandb.com/integrations/jupyter.html\" target=\"_blank\">(Documentation)</a>.<br/>\n",
+       "                Project page: <a href=\"https://wandb.ai/wandb/xlsr-nahuatl\" target=\"_blank\">https://wandb.ai/wandb/xlsr-nahuatl</a><br/>\n",
+       "                Run page: <a href=\"https://wandb.ai/wandb/xlsr-nahuatl/runs/qtdaydv0\" target=\"_blank\">https://wandb.ai/wandb/xlsr-nahuatl/runs/qtdaydv0</a><br/>\n",
+       "                Run data is saved locally in <code>/home/tyoc213/Documents/github/hf-xlsr-wav2vec2/wandb/run-20210328_170529-qtdaydv0</code><br/><br/>\n",
+       "            "
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/tyoc213/miniconda3/envs/fastai/lib/python3.8/site-packages/torch/_tensor.py:565: UserWarning: floor_divide is deprecated, and will be removed in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values.\n",
+      "To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). (Triggered internally at  /pytorch/aten/src/ATen/native/BinaryOps.cpp:341.)\n",
+      "  return torch.floor_divide(self, other)\n",
+      "/home/tyoc213/miniconda3/envs/fastai/lib/python3.8/site-packages/torch/nn/modules/module.py:903: UserWarning: Using non-full backward hooks on a Module that does not return a single Tensor or a tuple of Tensors is deprecated and will be removed in future versions. This hook will be missing some of the grad_output. Please use register_full_backward_hook to get the documented behavior.\n",
+      "  warnings.warn(\"Using non-full backward hooks on a Module that does not return a \"\n",
+      "/home/tyoc213/miniconda3/envs/fastai/lib/python3.8/site-packages/torch/nn/modules/module.py:938: UserWarning: Using a non-full backward hook when the forward contains multiple autograd Nodes is deprecated and will be removed in future versions. This hook will be missing some grad_input. Please use register_full_backward_hook to get the documented behavior.\n",
+      "  warnings.warn(\"Using a non-full backward hook when the forward contains multiple autograd Nodes \"\n",
+      "/home/tyoc213/miniconda3/envs/fastai/lib/python3.8/site-packages/torch/optim/lr_scheduler.py:129: UserWarning: Detected call of `lr_scheduler.step()` before `optimizer.step()`. In PyTorch 1.1.0 and later, you should call them in the opposite order: `optimizer.step()` before `lr_scheduler.step()`.  Failure to do this will result in PyTorch skipping the first value of the learning rate schedule. See more details at https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate\n",
+      "  warnings.warn(\"Detected call of `lr_scheduler.step()` before `optimizer.step()`. \"\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "\n",
+       "    <div>\n",
+       "        <style>\n",
+       "            /* Turns off some styling */\n",
+       "            progress {\n",
+       "                /* gets rid of default border in Firefox and Opera. */\n",
+       "                border: none;\n",
+       "                /* Needs to be in here for Safari polyfill so background images work as expected. */\n",
+       "                background-size: auto;\n",
+       "            }\n",
+       "        </style>\n",
+       "      \n",
+       "      <progress value='2850' max='2850' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
+       "      [2850/2850 3:07:34, Epoch 150/150]\n",
+       "    </div>\n",
+       "    <table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: left;\">\n",
+       "      <th>Step</th>\n",
+       "      <th>Training Loss</th>\n",
+       "      <th>Validation Loss</th>\n",
+       "      <th>Wer</th>\n",
+       "      <th>Runtime</th>\n",
+       "      <th>Samples Per Second</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <td>25</td>\n",
+       "      <td>11.366900</td>\n",
+       "      <td>12.198175</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>6.323500</td>\n",
+       "      <td>15.814000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>50</td>\n",
+       "      <td>8.893400</td>\n",
+       "      <td>6.548320</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>6.380900</td>\n",
+       "      <td>15.672000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>75</td>\n",
+       "      <td>3.767400</td>\n",
+       "      <td>3.567832</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>6.476700</td>\n",
+       "      <td>15.440000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>100</td>\n",
+       "      <td>3.207700</td>\n",
+       "      <td>3.079134</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>6.317100</td>\n",
+       "      <td>15.830000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>125</td>\n",
+       "      <td>3.107900</td>\n",
+       "      <td>3.005143</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>6.372800</td>\n",
+       "      <td>15.692000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>150</td>\n",
+       "      <td>3.075400</td>\n",
+       "      <td>3.001107</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>6.433400</td>\n",
+       "      <td>15.544000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>175</td>\n",
+       "      <td>3.024700</td>\n",
+       "      <td>3.007463</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>6.370800</td>\n",
+       "      <td>15.697000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>200</td>\n",
+       "      <td>3.019000</td>\n",
+       "      <td>2.968710</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>6.401200</td>\n",
+       "      <td>15.622000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>225</td>\n",
+       "      <td>2.983500</td>\n",
+       "      <td>2.891491</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>6.343900</td>\n",
+       "      <td>15.763000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>250</td>\n",
+       "      <td>2.937100</td>\n",
+       "      <td>2.874106</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>6.378800</td>\n",
+       "      <td>15.677000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>275</td>\n",
+       "      <td>3.048700</td>\n",
+       "      <td>2.879405</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>6.340800</td>\n",
+       "      <td>15.771000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>300</td>\n",
+       "      <td>2.901900</td>\n",
+       "      <td>2.799050</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>6.346800</td>\n",
+       "      <td>15.756000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>325</td>\n",
+       "      <td>2.819400</td>\n",
+       "      <td>2.670958</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>6.305500</td>\n",
+       "      <td>15.859000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>350</td>\n",
+       "      <td>2.604400</td>\n",
+       "      <td>2.246659</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>6.341800</td>\n",
+       "      <td>15.768000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>375</td>\n",
+       "      <td>1.936800</td>\n",
+       "      <td>1.614554</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>6.562300</td>\n",
+       "      <td>15.239000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>400</td>\n",
+       "      <td>1.751000</td>\n",
+       "      <td>1.355144</td>\n",
+       "      <td>0.971246</td>\n",
+       "      <td>6.487900</td>\n",
+       "      <td>15.413000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>425</td>\n",
+       "      <td>1.225900</td>\n",
+       "      <td>1.164381</td>\n",
+       "      <td>0.926518</td>\n",
+       "      <td>6.417800</td>\n",
+       "      <td>15.582000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>450</td>\n",
+       "      <td>1.206200</td>\n",
+       "      <td>1.053124</td>\n",
+       "      <td>0.851438</td>\n",
+       "      <td>6.428800</td>\n",
+       "      <td>15.555000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>475</td>\n",
+       "      <td>1.086200</td>\n",
+       "      <td>1.068727</td>\n",
+       "      <td>0.862620</td>\n",
+       "      <td>15.120200</td>\n",
+       "      <td>6.614000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>500</td>\n",
+       "      <td>0.714600</td>\n",
+       "      <td>0.950767</td>\n",
+       "      <td>0.736422</td>\n",
+       "      <td>6.375200</td>\n",
+       "      <td>15.686000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>525</td>\n",
+       "      <td>0.548800</td>\n",
+       "      <td>0.926604</td>\n",
+       "      <td>0.702875</td>\n",
+       "      <td>6.428700</td>\n",
+       "      <td>15.555000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>550</td>\n",
+       "      <td>0.702700</td>\n",
+       "      <td>0.902808</td>\n",
+       "      <td>0.726837</td>\n",
+       "      <td>6.327000</td>\n",
+       "      <td>15.805000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>575</td>\n",
+       "      <td>0.580500</td>\n",
+       "      <td>0.931756</td>\n",
+       "      <td>0.709265</td>\n",
+       "      <td>6.401400</td>\n",
+       "      <td>15.622000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>600</td>\n",
+       "      <td>0.458200</td>\n",
+       "      <td>0.928640</td>\n",
+       "      <td>0.661342</td>\n",
+       "      <td>6.393400</td>\n",
+       "      <td>15.641000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>625</td>\n",
+       "      <td>0.437800</td>\n",
+       "      <td>0.837019</td>\n",
+       "      <td>0.629393</td>\n",
+       "      <td>10.844000</td>\n",
+       "      <td>9.222000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>650</td>\n",
+       "      <td>0.340200</td>\n",
+       "      <td>0.882790</td>\n",
+       "      <td>0.626198</td>\n",
+       "      <td>6.382100</td>\n",
+       "      <td>15.669000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>675</td>\n",
+       "      <td>0.396800</td>\n",
+       "      <td>0.954396</td>\n",
+       "      <td>0.607029</td>\n",
+       "      <td>6.462400</td>\n",
+       "      <td>15.474000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>700</td>\n",
+       "      <td>0.320300</td>\n",
+       "      <td>0.934861</td>\n",
+       "      <td>0.599042</td>\n",
+       "      <td>6.424100</td>\n",
+       "      <td>15.566000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>725</td>\n",
+       "      <td>0.281600</td>\n",
+       "      <td>0.928510</td>\n",
+       "      <td>0.618211</td>\n",
+       "      <td>6.440300</td>\n",
+       "      <td>15.527000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>750</td>\n",
+       "      <td>0.261200</td>\n",
+       "      <td>1.002338</td>\n",
+       "      <td>0.623003</td>\n",
+       "      <td>6.399400</td>\n",
+       "      <td>15.627000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>775</td>\n",
+       "      <td>0.337400</td>\n",
+       "      <td>0.981839</td>\n",
+       "      <td>0.567093</td>\n",
+       "      <td>6.484400</td>\n",
+       "      <td>15.422000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>800</td>\n",
+       "      <td>0.218500</td>\n",
+       "      <td>1.015041</td>\n",
+       "      <td>0.594249</td>\n",
+       "      <td>6.487700</td>\n",
+       "      <td>15.414000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>825</td>\n",
+       "      <td>0.231000</td>\n",
+       "      <td>1.053406</td>\n",
+       "      <td>0.615016</td>\n",
+       "      <td>6.471500</td>\n",
+       "      <td>15.452000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>850</td>\n",
+       "      <td>0.351300</td>\n",
+       "      <td>1.061070</td>\n",
+       "      <td>0.605431</td>\n",
+       "      <td>6.584800</td>\n",
+       "      <td>15.187000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>875</td>\n",
+       "      <td>0.204500</td>\n",
+       "      <td>1.002169</td>\n",
+       "      <td>0.581470</td>\n",
+       "      <td>6.394800</td>\n",
+       "      <td>15.638000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>900</td>\n",
+       "      <td>0.169600</td>\n",
+       "      <td>1.048507</td>\n",
+       "      <td>0.579872</td>\n",
+       "      <td>6.525900</td>\n",
+       "      <td>15.324000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>925</td>\n",
+       "      <td>0.148300</td>\n",
+       "      <td>1.049545</td>\n",
+       "      <td>0.562300</td>\n",
+       "      <td>6.509800</td>\n",
+       "      <td>15.361000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>950</td>\n",
+       "      <td>0.255500</td>\n",
+       "      <td>1.005694</td>\n",
+       "      <td>0.554313</td>\n",
+       "      <td>9.091400</td>\n",
+       "      <td>10.999000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>975</td>\n",
+       "      <td>0.140900</td>\n",
+       "      <td>1.038244</td>\n",
+       "      <td>0.573482</td>\n",
+       "      <td>6.498400</td>\n",
+       "      <td>15.388000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1000</td>\n",
+       "      <td>0.144600</td>\n",
+       "      <td>1.076231</td>\n",
+       "      <td>0.563898</td>\n",
+       "      <td>6.550000</td>\n",
+       "      <td>15.267000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1025</td>\n",
+       "      <td>0.122700</td>\n",
+       "      <td>1.033349</td>\n",
+       "      <td>0.591054</td>\n",
+       "      <td>6.464800</td>\n",
+       "      <td>15.468000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1050</td>\n",
+       "      <td>0.119400</td>\n",
+       "      <td>0.984395</td>\n",
+       "      <td>0.555911</td>\n",
+       "      <td>6.472200</td>\n",
+       "      <td>15.451000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1075</td>\n",
+       "      <td>0.111600</td>\n",
+       "      <td>1.022373</td>\n",
+       "      <td>0.559105</td>\n",
+       "      <td>6.492800</td>\n",
+       "      <td>15.402000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1100</td>\n",
+       "      <td>0.133500</td>\n",
+       "      <td>1.031878</td>\n",
+       "      <td>0.527157</td>\n",
+       "      <td>6.505500</td>\n",
+       "      <td>15.372000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1125</td>\n",
+       "      <td>0.134800</td>\n",
+       "      <td>1.015920</td>\n",
+       "      <td>0.546326</td>\n",
+       "      <td>6.509400</td>\n",
+       "      <td>15.362000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1150</td>\n",
+       "      <td>0.138900</td>\n",
+       "      <td>1.076714</td>\n",
+       "      <td>0.560703</td>\n",
+       "      <td>6.461300</td>\n",
+       "      <td>15.477000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1175</td>\n",
+       "      <td>0.088400</td>\n",
+       "      <td>1.031096</td>\n",
+       "      <td>0.551118</td>\n",
+       "      <td>6.499800</td>\n",
+       "      <td>15.385000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1200</td>\n",
+       "      <td>0.129400</td>\n",
+       "      <td>1.069921</td>\n",
+       "      <td>0.544728</td>\n",
+       "      <td>6.523700</td>\n",
+       "      <td>15.329000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1225</td>\n",
+       "      <td>0.074900</td>\n",
+       "      <td>1.014724</td>\n",
+       "      <td>0.538339</td>\n",
+       "      <td>6.513400</td>\n",
+       "      <td>15.353000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1250</td>\n",
+       "      <td>0.086400</td>\n",
+       "      <td>1.063559</td>\n",
+       "      <td>0.539936</td>\n",
+       "      <td>6.456200</td>\n",
+       "      <td>15.489000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1275</td>\n",
+       "      <td>0.106000</td>\n",
+       "      <td>1.105790</td>\n",
+       "      <td>0.554313</td>\n",
+       "      <td>6.531100</td>\n",
+       "      <td>15.311000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1300</td>\n",
+       "      <td>0.062600</td>\n",
+       "      <td>1.120945</td>\n",
+       "      <td>0.539936</td>\n",
+       "      <td>6.479700</td>\n",
+       "      <td>15.433000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1325</td>\n",
+       "      <td>0.071500</td>\n",
+       "      <td>1.138995</td>\n",
+       "      <td>0.549521</td>\n",
+       "      <td>6.541600</td>\n",
+       "      <td>15.287000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1350</td>\n",
+       "      <td>0.060600</td>\n",
+       "      <td>1.056333</td>\n",
+       "      <td>0.562300</td>\n",
+       "      <td>6.503000</td>\n",
+       "      <td>15.377000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1375</td>\n",
+       "      <td>0.088100</td>\n",
+       "      <td>1.086479</td>\n",
+       "      <td>0.546326</td>\n",
+       "      <td>6.518000</td>\n",
+       "      <td>15.342000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1400</td>\n",
+       "      <td>0.069600</td>\n",
+       "      <td>1.077445</td>\n",
+       "      <td>0.555911</td>\n",
+       "      <td>6.557000</td>\n",
+       "      <td>15.251000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1425</td>\n",
+       "      <td>0.040700</td>\n",
+       "      <td>1.134361</td>\n",
+       "      <td>0.546326</td>\n",
+       "      <td>6.588800</td>\n",
+       "      <td>15.177000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1450</td>\n",
+       "      <td>0.033000</td>\n",
+       "      <td>1.141322</td>\n",
+       "      <td>0.546326</td>\n",
+       "      <td>6.519200</td>\n",
+       "      <td>15.339000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1475</td>\n",
+       "      <td>0.084200</td>\n",
+       "      <td>1.095898</td>\n",
+       "      <td>0.552716</td>\n",
+       "      <td>6.465900</td>\n",
+       "      <td>15.466000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1500</td>\n",
+       "      <td>0.040600</td>\n",
+       "      <td>1.048604</td>\n",
+       "      <td>0.517572</td>\n",
+       "      <td>6.606400</td>\n",
+       "      <td>15.137000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1525</td>\n",
+       "      <td>0.070700</td>\n",
+       "      <td>1.059956</td>\n",
+       "      <td>0.523962</td>\n",
+       "      <td>6.589700</td>\n",
+       "      <td>15.175000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1550</td>\n",
+       "      <td>0.068000</td>\n",
+       "      <td>1.103223</td>\n",
+       "      <td>0.541534</td>\n",
+       "      <td>6.489700</td>\n",
+       "      <td>15.409000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1575</td>\n",
+       "      <td>0.076000</td>\n",
+       "      <td>1.152243</td>\n",
+       "      <td>0.527157</td>\n",
+       "      <td>6.489000</td>\n",
+       "      <td>15.411000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1600</td>\n",
+       "      <td>0.032700</td>\n",
+       "      <td>1.136158</td>\n",
+       "      <td>0.546326</td>\n",
+       "      <td>6.532200</td>\n",
+       "      <td>15.309000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1625</td>\n",
+       "      <td>0.044200</td>\n",
+       "      <td>1.145053</td>\n",
+       "      <td>0.544728</td>\n",
+       "      <td>6.544200</td>\n",
+       "      <td>15.281000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1650</td>\n",
+       "      <td>0.077900</td>\n",
+       "      <td>1.062778</td>\n",
+       "      <td>0.541534</td>\n",
+       "      <td>6.671400</td>\n",
+       "      <td>14.989000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1675</td>\n",
+       "      <td>0.078000</td>\n",
+       "      <td>1.094251</td>\n",
+       "      <td>0.533546</td>\n",
+       "      <td>6.434200</td>\n",
+       "      <td>15.542000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1700</td>\n",
+       "      <td>0.037900</td>\n",
+       "      <td>1.116534</td>\n",
+       "      <td>0.533546</td>\n",
+       "      <td>6.431300</td>\n",
+       "      <td>15.549000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1725</td>\n",
+       "      <td>0.043000</td>\n",
+       "      <td>1.094801</td>\n",
+       "      <td>0.535144</td>\n",
+       "      <td>6.522600</td>\n",
+       "      <td>15.331000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1750</td>\n",
+       "      <td>0.069100</td>\n",
+       "      <td>1.142391</td>\n",
+       "      <td>0.563898</td>\n",
+       "      <td>6.496700</td>\n",
+       "      <td>15.392000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1775</td>\n",
+       "      <td>0.040600</td>\n",
+       "      <td>1.074260</td>\n",
+       "      <td>0.530351</td>\n",
+       "      <td>6.552000</td>\n",
+       "      <td>15.263000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1800</td>\n",
+       "      <td>0.083000</td>\n",
+       "      <td>1.131897</td>\n",
+       "      <td>0.539936</td>\n",
+       "      <td>6.527000</td>\n",
+       "      <td>15.321000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1825</td>\n",
+       "      <td>0.025000</td>\n",
+       "      <td>1.152289</td>\n",
+       "      <td>0.538339</td>\n",
+       "      <td>6.526700</td>\n",
+       "      <td>15.322000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1850</td>\n",
+       "      <td>0.097000</td>\n",
+       "      <td>1.150665</td>\n",
+       "      <td>0.551118</td>\n",
+       "      <td>6.517100</td>\n",
+       "      <td>15.344000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1875</td>\n",
+       "      <td>0.048900</td>\n",
+       "      <td>1.141236</td>\n",
+       "      <td>0.551118</td>\n",
+       "      <td>6.523800</td>\n",
+       "      <td>15.329000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1900</td>\n",
+       "      <td>0.070700</td>\n",
+       "      <td>1.133968</td>\n",
+       "      <td>0.544728</td>\n",
+       "      <td>6.477200</td>\n",
+       "      <td>15.439000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1925</td>\n",
+       "      <td>0.047500</td>\n",
+       "      <td>1.146004</td>\n",
+       "      <td>0.539936</td>\n",
+       "      <td>6.488000</td>\n",
+       "      <td>15.413000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1950</td>\n",
+       "      <td>0.035000</td>\n",
+       "      <td>1.142349</td>\n",
+       "      <td>0.522364</td>\n",
+       "      <td>6.502300</td>\n",
+       "      <td>15.379000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1975</td>\n",
+       "      <td>0.029600</td>\n",
+       "      <td>1.144181</td>\n",
+       "      <td>0.533546</td>\n",
+       "      <td>6.987000</td>\n",
+       "      <td>14.312000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2000</td>\n",
+       "      <td>0.119800</td>\n",
+       "      <td>1.116350</td>\n",
+       "      <td>0.527157</td>\n",
+       "      <td>6.609900</td>\n",
+       "      <td>15.129000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2025</td>\n",
+       "      <td>0.038500</td>\n",
+       "      <td>1.119617</td>\n",
+       "      <td>0.520767</td>\n",
+       "      <td>6.670800</td>\n",
+       "      <td>14.991000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2050</td>\n",
+       "      <td>0.063600</td>\n",
+       "      <td>1.143784</td>\n",
+       "      <td>0.527157</td>\n",
+       "      <td>6.546300</td>\n",
+       "      <td>15.276000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2075</td>\n",
+       "      <td>0.063300</td>\n",
+       "      <td>1.125548</td>\n",
+       "      <td>0.533546</td>\n",
+       "      <td>6.500300</td>\n",
+       "      <td>15.384000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2100</td>\n",
+       "      <td>0.050400</td>\n",
+       "      <td>1.104051</td>\n",
+       "      <td>0.530351</td>\n",
+       "      <td>6.629900</td>\n",
+       "      <td>15.083000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2125</td>\n",
+       "      <td>0.023500</td>\n",
+       "      <td>1.089869</td>\n",
+       "      <td>0.514377</td>\n",
+       "      <td>6.518300</td>\n",
+       "      <td>15.341000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2150</td>\n",
+       "      <td>0.070400</td>\n",
+       "      <td>1.125813</td>\n",
+       "      <td>0.515974</td>\n",
+       "      <td>6.535900</td>\n",
+       "      <td>15.300000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2175</td>\n",
+       "      <td>0.038900</td>\n",
+       "      <td>1.137404</td>\n",
+       "      <td>0.509585</td>\n",
+       "      <td>6.532500</td>\n",
+       "      <td>15.308000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2200</td>\n",
+       "      <td>0.014800</td>\n",
+       "      <td>1.136877</td>\n",
+       "      <td>0.512780</td>\n",
+       "      <td>6.597900</td>\n",
+       "      <td>15.156000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2225</td>\n",
+       "      <td>0.055900</td>\n",
+       "      <td>1.149602</td>\n",
+       "      <td>0.523962</td>\n",
+       "      <td>6.552800</td>\n",
+       "      <td>15.261000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2250</td>\n",
+       "      <td>0.029100</td>\n",
+       "      <td>1.149819</td>\n",
+       "      <td>0.523962</td>\n",
+       "      <td>6.607500</td>\n",
+       "      <td>15.134000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2275</td>\n",
+       "      <td>0.064200</td>\n",
+       "      <td>1.164270</td>\n",
+       "      <td>0.523962</td>\n",
+       "      <td>6.538200</td>\n",
+       "      <td>15.295000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2300</td>\n",
+       "      <td>0.037400</td>\n",
+       "      <td>1.153843</td>\n",
+       "      <td>0.522364</td>\n",
+       "      <td>6.519000</td>\n",
+       "      <td>15.340000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2325</td>\n",
+       "      <td>0.013400</td>\n",
+       "      <td>1.148319</td>\n",
+       "      <td>0.520767</td>\n",
+       "      <td>6.619100</td>\n",
+       "      <td>15.108000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2350</td>\n",
+       "      <td>0.139100</td>\n",
+       "      <td>1.144181</td>\n",
+       "      <td>0.523962</td>\n",
+       "      <td>6.464000</td>\n",
+       "      <td>15.470000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2375</td>\n",
+       "      <td>0.030800</td>\n",
+       "      <td>1.104669</td>\n",
+       "      <td>0.525559</td>\n",
+       "      <td>6.475400</td>\n",
+       "      <td>15.443000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2400</td>\n",
+       "      <td>0.038100</td>\n",
+       "      <td>1.100786</td>\n",
+       "      <td>0.520767</td>\n",
+       "      <td>6.478100</td>\n",
+       "      <td>15.437000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2425</td>\n",
+       "      <td>0.052800</td>\n",
+       "      <td>1.126264</td>\n",
+       "      <td>0.525559</td>\n",
+       "      <td>6.529500</td>\n",
+       "      <td>15.315000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2450</td>\n",
+       "      <td>0.027900</td>\n",
+       "      <td>1.108293</td>\n",
+       "      <td>0.515974</td>\n",
+       "      <td>6.519900</td>\n",
+       "      <td>15.338000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2475</td>\n",
+       "      <td>0.014700</td>\n",
+       "      <td>1.102872</td>\n",
+       "      <td>0.520767</td>\n",
+       "      <td>6.517100</td>\n",
+       "      <td>15.344000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2500</td>\n",
+       "      <td>0.046300</td>\n",
+       "      <td>1.104023</td>\n",
+       "      <td>0.517572</td>\n",
+       "      <td>6.513400</td>\n",
+       "      <td>15.353000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2525</td>\n",
+       "      <td>0.059400</td>\n",
+       "      <td>1.134425</td>\n",
+       "      <td>0.520767</td>\n",
+       "      <td>6.583700</td>\n",
+       "      <td>15.189000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2550</td>\n",
+       "      <td>0.055200</td>\n",
+       "      <td>1.132238</td>\n",
+       "      <td>0.525559</td>\n",
+       "      <td>6.544900</td>\n",
+       "      <td>15.279000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2575</td>\n",
+       "      <td>0.033600</td>\n",
+       "      <td>1.122662</td>\n",
+       "      <td>0.523962</td>\n",
+       "      <td>6.552500</td>\n",
+       "      <td>15.261000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2600</td>\n",
+       "      <td>0.024400</td>\n",
+       "      <td>1.129860</td>\n",
+       "      <td>0.514377</td>\n",
+       "      <td>6.604100</td>\n",
+       "      <td>15.142000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2625</td>\n",
+       "      <td>0.033700</td>\n",
+       "      <td>1.123130</td>\n",
+       "      <td>0.509585</td>\n",
+       "      <td>6.593500</td>\n",
+       "      <td>15.166000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2650</td>\n",
+       "      <td>0.037700</td>\n",
+       "      <td>1.121162</td>\n",
+       "      <td>0.515974</td>\n",
+       "      <td>6.581100</td>\n",
+       "      <td>15.195000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2675</td>\n",
+       "      <td>0.045200</td>\n",
+       "      <td>1.115516</td>\n",
+       "      <td>0.517572</td>\n",
+       "      <td>6.590400</td>\n",
+       "      <td>15.174000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2700</td>\n",
+       "      <td>0.021400</td>\n",
+       "      <td>1.125632</td>\n",
+       "      <td>0.515974</td>\n",
+       "      <td>6.559800</td>\n",
+       "      <td>15.244000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2725</td>\n",
+       "      <td>0.041100</td>\n",
+       "      <td>1.132779</td>\n",
+       "      <td>0.515974</td>\n",
+       "      <td>6.513400</td>\n",
+       "      <td>15.353000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2750</td>\n",
+       "      <td>0.036900</td>\n",
+       "      <td>1.132278</td>\n",
+       "      <td>0.515974</td>\n",
+       "      <td>6.592900</td>\n",
+       "      <td>15.168000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2775</td>\n",
+       "      <td>0.045000</td>\n",
+       "      <td>1.118795</td>\n",
+       "      <td>0.515974</td>\n",
+       "      <td>6.645000</td>\n",
+       "      <td>15.049000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2800</td>\n",
+       "      <td>0.049400</td>\n",
+       "      <td>1.119261</td>\n",
+       "      <td>0.517572</td>\n",
+       "      <td>6.476900</td>\n",
+       "      <td>15.439000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2825</td>\n",
+       "      <td>0.033700</td>\n",
+       "      <td>1.118214</td>\n",
+       "      <td>0.517572</td>\n",
+       "      <td>6.475500</td>\n",
+       "      <td>15.443000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2850</td>\n",
+       "      <td>0.041000</td>\n",
+       "      <td>1.118845</td>\n",
+       "      <td>0.517572</td>\n",
+       "      <td>6.477300</td>\n",
+       "      <td>15.438000</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table><p>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": [
+       "TrainOutput(global_step=2850, training_loss=0.7157523092679811, metrics={'train_runtime': 11256.0194, 'train_samples_per_second': 0.253, 'total_flos': 1.3250501354353367e+19, 'epoch': 150.0, 'init_mem_cpu_alloc_delta': 60099, 'init_mem_gpu_alloc_delta': 1261939712, 'init_mem_cpu_peaked_delta': 18258, 'init_mem_gpu_peaked_delta': 0, 'train_mem_cpu_alloc_delta': 0, 'train_mem_gpu_alloc_delta': 5047669248, 'train_mem_cpu_peaked_delta': 0, 'train_mem_gpu_peaked_delta': 0})"
+      ]
+     },
+     "execution_count": 63,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "trainer.train()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 64,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<br/>Waiting for W&B process to finish, PID 11231<br/>Program ended successfully."
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "VBox(children=(Label(value=' 1252.74MB of 1252.74MB uploaded (0.62MB deduped)\\r'), FloatProgress(value=1.0, ma…"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "Find user logs for this run at: <code>/home/tyoc213/Documents/github/hf-xlsr-wav2vec2/wandb/run-20210328_170529-qtdaydv0/logs/debug.log</code>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "Find internal logs for this run at: <code>/home/tyoc213/Documents/github/hf-xlsr-wav2vec2/wandb/run-20210328_170529-qtdaydv0/logs/debug-internal.log</code>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<h3>Run summary:</h3><br/><style>\n",
+       "    table.wandb td:nth-child(1) { padding: 0 10px; text-align: right }\n",
+       "    </style><table class=\"wandb\">\n",
+       "<tr><td>train/loss</td><td>0.041</td></tr><tr><td>train/learning_rate</td><td>0.0</td></tr><tr><td>train/epoch</td><td>150.0</td></tr><tr><td>train/global_step</td><td>2850</td></tr><tr><td>_runtime</td><td>11256</td></tr><tr><td>_timestamp</td><td>1616983985</td></tr><tr><td>_step</td><td>684</td></tr><tr><td>eval/loss</td><td>1.11885</td></tr><tr><td>eval/wer</td><td>0.51757</td></tr><tr><td>eval/runtime</td><td>6.4773</td></tr><tr><td>eval/samples_per_second</td><td>15.438</td></tr><tr><td>train/train_runtime</td><td>11256.0194</td></tr><tr><td>train/train_samples_per_second</td><td>0.253</td></tr><tr><td>train/total_flos</td><td>1.3250501354353367e+19</td></tr></table>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<h3>Run history:</h3><br/><style>\n",
+       "    table.wandb td:nth-child(1) { padding: 0 10px; text-align: right }\n",
+       "    </style><table class=\"wandb\">\n",
+       "<tr><td>train/loss</td><td>█▃▃▃▃▂▂▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁</td></tr><tr><td>train/learning_rate</td><td>▂▄▇███▇▇▇▇▇▆▆▆▆▆▆▅▅▅▅▅▄▄▄▄▄▃▃▃▃▃▂▂▂▂▂▁▁▁</td></tr><tr><td>train/epoch</td><td>▁▁▁▂▂▂▂▂▂▃▃▃▃▃▃▄▄▄▄▄▅▅▅▅▅▅▆▆▆▆▆▆▇▇▇▇▇███</td></tr><tr><td>train/global_step</td><td>▁▁▁▁▂▂▂▂▂▃▃▃▃▃▃▄▄▄▄▄▅▅▅▅▅▅▆▆▆▆▆▇▇▇▇▇▇███</td></tr><tr><td>_runtime</td><td>▁▁▁▁▂▂▂▂▃▃▃▃▃▄▄▄▄▄▅▅▅▅▅▅▆▆▆▆▆▆▆▇▇▇▇▇▇███</td></tr><tr><td>_timestamp</td><td>▁▁▁▁▂▂▂▂▃▃▃▃▃▄▄▄▄▄▅▅▅▅▅▅▆▆▆▆▆▆▆▇▇▇▇▇▇███</td></tr><tr><td>_step</td><td>▁▁▁▁▂▂▂▂▂▃▃▃▃▃▃▄▄▄▄▄▅▅▅▅▅▅▆▆▆▆▆▇▇▇▇▇▇███</td></tr><tr><td>eval/loss</td><td>█▃▂▂▂▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁</td></tr><tr><td>eval/wer</td><td>████���█▆▄▃▂▃▂▂▂▂▁▂▁▂▂▂▁▂▁▂▁▂▁▁▁▁▁▁▁▁▁▁▁▁▁</td></tr><tr><td>eval/runtime</td><td>▁▁▁▁▁▂▁▁▁▁▁▁▁█▁▁▁▁▂▂▁▂▂▁▁▂▁▃▂▁▂▂▂▁▁▂▂▂▂▁</td></tr><tr><td>eval/samples_per_second</td><td>█▇███▇█████▇█▁▇▇▇█▇▇▇▇▇█▇▇▇▆▇▇▇▇▇▇▇▇▇▇▇▇</td></tr><tr><td>train/train_runtime</td><td>▁</td></tr><tr><td>train/train_samples_per_second</td><td>▁</td></tr><tr><td>train/total_flos</td><td>▁</td></tr></table><br/>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "Synced 5 W&B file(s), 1 media file(s), 6 artifact file(s) and 1 other file(s)"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "\n",
+       "                    <br/>Synced <strong style=\"color:#cdcd00\">final0-wav2vec2-large-xlsr-nahuatl-es-de--one-ie-base-50e-ovh-4-4-upgrade</strong>: <a href=\"https://wandb.ai/wandb/xlsr-nahuatl/runs/qtdaydv0\" target=\"_blank\">https://wandb.ai/wandb/xlsr-nahuatl/runs/qtdaydv0</a><br/>\n",
+       "                "
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 7.33 s, sys: 560 ms, total: 7.89 s\n",
+      "Wall time: 10min 17s\n"
+     ]
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "wandb.finish()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "accelerator": "GPU",
+  "colab": {
+   "collapsed_sections": [],
+   "machine_shape": "hm",
+   "name": "Fine-Tune XLSR-Wav2Vec2 on Turkish ASR with 🤗 Transformers.ipynb",
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.5"
+  },
+  "widgets": {
+   "application/vnd.jupyter.widget-state+json": {
+    "015c5690e1ea4281954c7efda1c80a6a": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "FloatProgressModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "FloatProgressModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "ProgressView",
+      "bar_style": "success",
+      "description": "#1: 100%",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_dec796237765477ea904834d9a824b61",
+      "max": 109,
+      "min": 0,
+      "orientation": "horizontal",
+      "style": "IPY_MODEL_2f727c76652944e3892dd584bea11af2",
+      "value": 109
+     }
+    },
+    "018c1f8e198e4df4b480e609bd1be602": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HTMLModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_768ab09956774f50a79b2493a8bf179b",
+      "placeholder": "​",
+      "style": "IPY_MODEL_d35c15beeb33476894b07c3563f8facd",
+      "value": " 109/109 [00:56&lt;00:00,  1.92ba/s]"
+     }
+    },
+    "020bdb330b0d40f5b89697ff37025f69": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "024989cea06f435894776b0a921164b2": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "ProgressStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "ProgressStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "bar_color": null,
+      "description_width": "initial"
+     }
+    },
+    "02bdb06c176145feaa842b97ae58609c": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "DescriptionStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "DescriptionStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "description_width": ""
+     }
+    },
+    "02d1f77324854fbca0df9384c57faac8": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "FloatProgressModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "FloatProgressModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "ProgressView",
+      "bar_style": "success",
+      "description": "#3: 100%",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_d4a3f79644fc41848450ba29e6fdfc3d",
+      "max": 52,
+      "min": 0,
+      "orientation": "horizontal",
+      "style": "IPY_MODEL_704ea5e05fd744d998b76d6435992995",
+      "value": 52
+     }
+    },
+    "0354ab33471e4c34a0c1b3c062bcd6bb": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "03b33c17734d49e28c4636dddd6e833d": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "FloatProgressModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "FloatProgressModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "ProgressView",
+      "bar_style": "info",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_bee0f50055eb4f738636142a10da0ddd",
+      "max": 1,
+      "min": 0,
+      "orientation": "horizontal",
+      "style": "IPY_MODEL_da1ff50f8b9241108a325ada04224642",
+      "value": 1
+     }
+    },
+    "05f83d714f864a399083f0e34a812467": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "DescriptionStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "DescriptionStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "description_width": ""
+     }
+    },
+    "089428f56e66419f85ea149d9d102454": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HBoxModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HBoxModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HBoxView",
+      "box_style": "",
+      "children": [
+       "IPY_MODEL_4db5037af3f64a3a8a8a1203018a80ff",
+       "IPY_MODEL_6a957c1c17474d8d89c27ddecf702fda"
+      ],
+      "layout": "IPY_MODEL_d649c0f9c1c24634a84b7ef697721ffa"
+     }
+    },
+    "0987aac282af415da2fbc9dc1b4d5069": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "0a9b58c98508420d8f8936189f064316": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "FloatProgressModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "FloatProgressModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "ProgressView",
+      "bar_style": "info",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_af85713f677243d19cba9fe69a4a5f46",
+      "max": 1,
+      "min": 0,
+      "orientation": "horizontal",
+      "style": "IPY_MODEL_c546bca23ee248a1be7bd8ead3e82a8f",
+      "value": 1
+     }
+    },
+    "0b795d4b68014de19bf9579c67b55ffb": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "DescriptionStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "DescriptionStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "description_width": ""
+     }
+    },
+    "0cd1932178c945d48604ffd299e65d2c": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "0e999af234bd4b63ad2937e61d08b693": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "0f3756509e3b405d87936f599b153de2": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "0f99011a13754ed99f3c51a478b0e793": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HBoxModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HBoxModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HBoxView",
+      "box_style": "",
+      "children": [
+       "IPY_MODEL_bd187486ac2548f2961cfcb63d852de1",
+       "IPY_MODEL_3f780f0aa8834fc189b292e0474e2ffa"
+      ],
+      "layout": "IPY_MODEL_4abe2731ec624729b401d60a392cae63"
+     }
+    },
+    "0ffcbedb8d4444508ac0c3c0b41ea8ac": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "1261590ef796493798f7068ea0547b74": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "ProgressStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "ProgressStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "bar_color": null,
+      "description_width": "initial"
+     }
+    },
+    "12696cc03f464a63a411efb2b5e5ac3b": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HTMLModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_ceb44ba4fdf34da19a52469acf1ce63f",
+      "placeholder": "​",
+      "style": "IPY_MODEL_68a3178fe7a54e838e798ff28ff9aa0b",
+      "value": " 139k/? [00:00&lt;00:00, 2.38MB/s]"
+     }
+    },
+    "1813458f75514f039ba0214597a09bb4": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "19e263785ea343ba99ee2127d9b83d1d": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "DescriptionStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "DescriptionStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "description_width": ""
+     }
+    },
+    "1f1faa7b986e475c9e6839b2e7b55c74": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HTMLModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_b320306eaf264ad9872d507a1a1cb2da",
+      "placeholder": "​",
+      "style": "IPY_MODEL_2ca2f397c4ef405bba27ae2b1415cada",
+      "value": " 3478/3478 [03:59&lt;00:00, 14.53ex/s]"
+     }
+    },
+    "20347ed29fdc4c0a96da28c09aacf44d": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "DescriptionStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "DescriptionStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "description_width": ""
+     }
+    },
+    "231c66f195d34f86b216805518f4bccd": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "ProgressStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "ProgressStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "bar_color": null,
+      "description_width": "initial"
+     }
+    },
+    "24ea17ae8ab14e8a871e5e115c3f4c06": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HBoxModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HBoxModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HBoxView",
+      "box_style": "",
+      "children": [
+       "IPY_MODEL_f3905820a42c499fba04af9c1ad19705",
+       "IPY_MODEL_4e1a725fd90b45e280b8b0028ba65250"
+      ],
+      "layout": "IPY_MODEL_f57d087016124ebeb073fd7428dcb68b"
+     }
+    },
+    "25ba4f4c8b9c44af9885b3903a9261fd": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HBoxModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HBoxModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HBoxView",
+      "box_style": "",
+      "children": [
+       "IPY_MODEL_03b33c17734d49e28c4636dddd6e833d",
+       "IPY_MODEL_71c059a0f3c246f3a40d55744331daaa"
+      ],
+      "layout": "IPY_MODEL_dde7ae43ef954ef1b901c80f0a4e11fd"
+     }
+    },
+    "26e7bab0f3bf4797bfcef83dcace24f0": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "2a6e1185a6a247f5acba8111824ad36b": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "ProgressStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "ProgressStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "bar_color": null,
+      "description_width": "initial"
+     }
+    },
+    "2ca2f397c4ef405bba27ae2b1415cada": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "DescriptionStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "DescriptionStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "description_width": ""
+     }
+    },
+    "2cd13e03a2ab45dc8570c8c739a613b4": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "2f18d89c684343b69c3f44ffbb9b42a0": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "DescriptionStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "DescriptionStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "description_width": ""
+     }
+    },
+    "2f5406546970425282a881b5d2f7c248": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "2f727c76652944e3892dd584bea11af2": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "ProgressStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "ProgressStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "bar_color": null,
+      "description_width": "initial"
+     }
+    },
+    "2fd148d5587b4139919b0158f9dad71e": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "304e9130c12f4110941bfbd3db49a28c": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HBoxModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HBoxModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HBoxView",
+      "box_style": "",
+      "children": [
+       "IPY_MODEL_75e00c38605f44cfb584067db1160349",
+       "IPY_MODEL_8c07a528fc4a4e108b393ab117fe2e46"
+      ],
+      "layout": "IPY_MODEL_5e6bae23461b4378b6e5fc890fe6bc97"
+     }
+    },
+    "3133b378b9294a759c8dfb786ed8f815": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "ProgressStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "ProgressStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "bar_color": null,
+      "description_width": "initial"
+     }
+    },
+    "330226a977694de1bd88c0aa3789be47": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "33c92b5afd1d4b6d88016aabfb434194": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "FloatProgressModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "FloatProgressModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "ProgressView",
+      "bar_style": "success",
+      "description": "100%",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_3dc9ea77b842455a91f00e9ca9f41948",
+      "max": 1647,
+      "min": 0,
+      "orientation": "horizontal",
+      "style": "IPY_MODEL_45f0a2f361da4608bc8314a27657a56c",
+      "value": 1647
+     }
+    },
+    "348ef54c80b2449f8a3bc950cccd62cc": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HBoxModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HBoxModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HBoxView",
+      "box_style": "",
+      "children": [
+       "IPY_MODEL_7edbecaccdd94ede8fddc0e1807e777e",
+       "IPY_MODEL_5e3aad95e52f4be2bd670d1345398f1b"
+      ],
+      "layout": "IPY_MODEL_b78413dcc0584a0c8f71731a06aaa1b8"
+     }
+    },
+    "389e43e47a734193a507817ebad955f7": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "3bdb4058f40f40e3a10e323325a64638": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HTMLModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_d7f27e9cf8a844349ca90393e0c49a03",
+      "placeholder": "​",
+      "style": "IPY_MODEL_751ae6b9e2da4b85be9600561485f1ac",
+      "value": " 412/412 [03:04&lt;00:00,  2.23ex/s]"
+     }
+    },
+    "3d929b9e2518402b81a71757ffb753d2": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "3dc9ea77b842455a91f00e9ca9f41948": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "3e2cd59ac697495f8db14b894b783f95": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "3e3a022a9f304b0f9f7ef067fcee1e56": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "3ec3285e9f3e4a5abcefabb7f140f4a3": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "ProgressStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "ProgressStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "bar_color": null,
+      "description_width": "initial"
+     }
+    },
+    "3f780f0aa8834fc189b292e0474e2ffa": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HTMLModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_a868dea9d9b047a4b853b390e138e4c1",
+      "placeholder": "​",
+      "style": "IPY_MODEL_ec36a94ee2574ac8b227ccaefdee5520",
+      "value": " 52/52 [00:31&lt;00:00,  1.67ba/s]"
+     }
+    },
+    "405b5de4ae854cf9896f63d15f2207dd": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "DescriptionStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "DescriptionStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "description_width": ""
+     }
+    },
+    "416badb151ee4660b53fdbc136e0c8fb": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HTMLModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_0f3756509e3b405d87936f599b153de2",
+      "placeholder": "​",
+      "style": "IPY_MODEL_824569c63ec445c08362659ca228dd2a",
+      "value": " 412/412 [03:01&lt;00:00,  2.28ex/s]"
+     }
+    },
+    "430c3c079d0e4006b90e72df7986ffb0": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "4382726ef043441a9b1a4a647d84f242": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "ProgressStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "ProgressStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "bar_color": null,
+      "description_width": "initial"
+     }
+    },
+    "45f0a2f361da4608bc8314a27657a56c": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "ProgressStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "ProgressStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "bar_color": null,
+      "description_width": "initial"
+     }
+    },
+    "4797f1acd9924b4e97f12f964c83078c": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HBoxModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HBoxModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HBoxView",
+      "box_style": "",
+      "children": [
+       "IPY_MODEL_5370c0f2d54b45c0a89f11fb5b70cd4b",
+       "IPY_MODEL_018c1f8e198e4df4b480e609bd1be602"
+      ],
+      "layout": "IPY_MODEL_73940df84ffd4e0f96637342e9fd12b7"
+     }
+    },
+    "47a6c3c427614f21a6dab1c048e5dd37": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "491fd969d61a478f8e85ffcd3e1a3e20": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "49defa4284554baf85f32de242b22709": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "ProgressStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "ProgressStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "bar_color": null,
+      "description_width": "initial"
+     }
+    },
+    "4abe2731ec624729b401d60a392cae63": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "4c0ad31e73234e46aac0a297ec18bdeb": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "ProgressStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "ProgressStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "bar_color": null,
+      "description_width": "initial"
+     }
+    },
+    "4db5037af3f64a3a8a8a1203018a80ff": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "FloatProgressModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "FloatProgressModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "ProgressView",
+      "bar_style": "info",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_c0e6b6e6395d4dbd827eb1c0de1ad21a",
+      "max": 1,
+      "min": 0,
+      "orientation": "horizontal",
+      "style": "IPY_MODEL_2a6e1185a6a247f5acba8111824ad36b",
+      "value": 1
+     }
+    },
+    "4e1a725fd90b45e280b8b0028ba65250": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HTMLModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_491fd969d61a478f8e85ffcd3e1a3e20",
+      "placeholder": "​",
+      "style": "IPY_MODEL_9f79629ad6a94201acf3283862d1ae17",
+      "value": " 869/869 [05:48&lt;00:00,  2.49ex/s]"
+     }
+    },
+    "4f8957dc035d4c1a9e8630fc8ab8cd10": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "FloatProgressModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "FloatProgressModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "ProgressView",
+      "bar_style": "success",
+      "description": "#1: 100%",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_47a6c3c427614f21a6dab1c048e5dd37",
+      "max": 870,
+      "min": 0,
+      "orientation": "horizontal",
+      "style": "IPY_MODEL_596aea0362924c7db583203268dd5a3e",
+      "value": 870
+     }
+    },
+    "4fb7347e9ca542e6ab9003bf4db218e0": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HTMLModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_0987aac282af415da2fbc9dc1b4d5069",
+      "placeholder": "​",
+      "style": "IPY_MODEL_6d4a26d876fb4ac6b5948a09945bdc6b",
+      "value": " 109/109 [00:58&lt;00:00,  1.88ba/s]"
+     }
+    },
+    "4ff7ccffc36a4a0f93031f5cdc3b718d": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "ProgressStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "ProgressStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "bar_color": null,
+      "description_width": "initial"
+     }
+    },
+    "5071a31d06f544a5b7340a4e863d8fdf": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "FloatProgressModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "FloatProgressModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "ProgressView",
+      "bar_style": "success",
+      "description": "#3: 100%",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_b2473405490e4556bf30c0cc81237aa5",
+      "max": 109,
+      "min": 0,
+      "orientation": "horizontal",
+      "style": "IPY_MODEL_49defa4284554baf85f32de242b22709",
+      "value": 109
+     }
+    },
+    "530f66ac087e4f8f979fcaa33941c60d": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "ProgressStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "ProgressStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "bar_color": null,
+      "description_width": "initial"
+     }
+    },
+    "5370c0f2d54b45c0a89f11fb5b70cd4b": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "FloatProgressModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "FloatProgressModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "ProgressView",
+      "bar_style": "success",
+      "description": "#0: 100%",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_020bdb330b0d40f5b89697ff37025f69",
+      "max": 109,
+      "min": 0,
+      "orientation": "horizontal",
+      "style": "IPY_MODEL_fa7926bbe77e48b3a0648b45f5d2dc7a",
+      "value": 109
+     }
+    },
+    "540510088d3947f1b3cf6f4c983c1a53": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "542027ba12f444d586e8072452badea0": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HTMLModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_bc41384bbae04044b9780651c6b5a47c",
+      "placeholder": "​",
+      "style": "IPY_MODEL_02bdb06c176145feaa842b97ae58609c",
+      "value": " 109/109 [00:58&lt;00:00,  1.88ba/s]"
+     }
+    },
+    "55071fc1b7484620803aeba453e9af72": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "56ad6231a0a04228be29ceecbc6b7c0e": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "57198e3250374e1fa64c5a4be255861e": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HTMLModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_8f737725708c4097a8caaf4da6229636",
+      "placeholder": "​",
+      "style": "IPY_MODEL_969080b52ad44ee997829986d198c505",
+      "value": " 3.90k/? [00:00&lt;00:00, 23.0kB/s]"
+     }
+    },
+    "579b6055028f473981ce789a0733a753": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "FloatProgressModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "FloatProgressModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "ProgressView",
+      "bar_style": "success",
+      "description": "#2: 100%",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_6de66d6b7a73434cbdc59b2109bdf0a0",
+      "max": 109,
+      "min": 0,
+      "orientation": "horizontal",
+      "style": "IPY_MODEL_3133b378b9294a759c8dfb786ed8f815",
+      "value": 109
+     }
+    },
+    "58f3e8002f984594ac05c973aa78ef69": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "596aea0362924c7db583203268dd5a3e": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "ProgressStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "ProgressStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "bar_color": null,
+      "description_width": "initial"
+     }
+    },
+    "59e0f5200068461cbfb256ad5479c4c8": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "DescriptionStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "DescriptionStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "description_width": ""
+     }
+    },
+    "5a5bc8b4a1c644dea08a60128d888d10": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "DescriptionStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "DescriptionStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "description_width": ""
+     }
+    },
+    "5ab30242cd154ec0b560c23c0f178546": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "ProgressStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "ProgressStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "bar_color": null,
+      "description_width": "initial"
+     }
+    },
+    "5ccd12253fff448f9c15c9b03c70a408": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HBoxModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HBoxModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HBoxView",
+      "box_style": "",
+      "children": [
+       "IPY_MODEL_f203c54e7e054d97aa4d1097f320f611",
+       "IPY_MODEL_6266a4019e124aff877bb55f21740180"
+      ],
+      "layout": "IPY_MODEL_330226a977694de1bd88c0aa3789be47"
+     }
+    },
+    "5e3aad95e52f4be2bd670d1345398f1b": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HTMLModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_99d5c44ea54b45ee9bd89380cb1ad189",
+      "placeholder": "​",
+      "style": "IPY_MODEL_7aa70322bdfe46938b583a20003093d5",
+      "value": " 3478/3478 [03:16&lt;00:00, 17.67ex/s]"
+     }
+    },
+    "5e6bae23461b4378b6e5fc890fe6bc97": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "5f48f54986924e418aa4ac22aa54b714": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HBoxModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HBoxModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HBoxView",
+      "box_style": "",
+      "children": [
+       "IPY_MODEL_a58c203a7cc54086aea45f2029821207",
+       "IPY_MODEL_8d409ca0372a48e2972ca1d8eee5ffa1"
+      ],
+      "layout": "IPY_MODEL_db71db50799c404aafa4a54de8b9b799"
+     }
+    },
+    "6266a4019e124aff877bb55f21740180": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HTMLModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_55071fc1b7484620803aeba453e9af72",
+      "placeholder": "​",
+      "style": "IPY_MODEL_8ad3e4b211e34c048d0f48e36fdbfe48",
+      "value": " 411/411 [02:58&lt;00:00,  2.30ex/s]"
+     }
+    },
+    "6462bd9561e24abb98fce6ce4675d810": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HBoxModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HBoxModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HBoxView",
+      "box_style": "",
+      "children": [
+       "IPY_MODEL_e273548a15aa4d4994132b317adb66fc",
+       "IPY_MODEL_f6930dd5519d4dfda64c597def220a30"
+      ],
+      "layout": "IPY_MODEL_bd3447291ce54812af10ac6245ea4328"
+     }
+    },
+    "68a3178fe7a54e838e798ff28ff9aa0b": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "DescriptionStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "DescriptionStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "description_width": ""
+     }
+    },
+    "69828f4a101f4340916a4be141866904": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "6a957c1c17474d8d89c27ddecf702fda": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HTMLModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_91fcf0641fe3489ab96f3aaa40adf245",
+      "placeholder": "​",
+      "style": "IPY_MODEL_05f83d714f864a399083f0e34a812467",
+      "value": " 1647/0 [00:00&lt;00:00, 14016.07 examples/s]"
+     }
+    },
+    "6abfbe44a1bd4518b41f5f53f920e936": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "6ba6d07674a34836be53cf173c2b61ca": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "6c065aa34661469ca1efb4c5e90fe136": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HBoxModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HBoxModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HBoxView",
+      "box_style": "",
+      "children": [
+       "IPY_MODEL_0a9b58c98508420d8f8936189f064316",
+       "IPY_MODEL_8dd5b08bb5bd4e608d04122424796ae7"
+      ],
+      "layout": "IPY_MODEL_540510088d3947f1b3cf6f4c983c1a53"
+     }
+    },
+    "6d4a26d876fb4ac6b5948a09945bdc6b": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "DescriptionStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "DescriptionStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "description_width": ""
+     }
+    },
+    "6de66d6b7a73434cbdc59b2109bdf0a0": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "6f60626242534f44a6381195e6eb6530": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "FloatProgressModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "FloatProgressModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "ProgressView",
+      "bar_style": "success",
+      "description": "#2: 100%",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_0ffcbedb8d4444508ac0c3c0b41ea8ac",
+      "max": 52,
+      "min": 0,
+      "orientation": "horizontal",
+      "style": "IPY_MODEL_5ab30242cd154ec0b560c23c0f178546",
+      "value": 52
+     }
+    },
+    "7040945accce4739a41746cc75bb7fce": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HBoxModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HBoxModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HBoxView",
+      "box_style": "",
+      "children": [
+       "IPY_MODEL_6f60626242534f44a6381195e6eb6530",
+       "IPY_MODEL_9fee9d9dd1164d97a9109e942444c332"
+      ],
+      "layout": "IPY_MODEL_71011f0d2bc942ac8f9ea1d1fd30c78d"
+     }
+    },
+    "704ea5e05fd744d998b76d6435992995": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "ProgressStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "ProgressStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "bar_color": null,
+      "description_width": "initial"
+     }
+    },
+    "71011f0d2bc942ac8f9ea1d1fd30c78d": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "71c059a0f3c246f3a40d55744331daaa": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HTMLModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_430c3c079d0e4006b90e72df7986ffb0",
+      "placeholder": "​",
+      "style": "IPY_MODEL_cb5666eb8ebb4d1392e98d6b5af8761c",
+      "value": " 325/0 [00:00&lt;00:00, 7071.04 examples/s]"
+     }
+    },
+    "71ffdf6f26ba4381a8e671958e679f88": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "ProgressStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "ProgressStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "bar_color": null,
+      "description_width": "initial"
+     }
+    },
+    "73940df84ffd4e0f96637342e9fd12b7": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "73ecbfc3c5c5456bb42e19b8a34b1576": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "751ae6b9e2da4b85be9600561485f1ac": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "DescriptionStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "DescriptionStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "description_width": ""
+     }
+    },
+    "757e7bd0e6c5410da0490d191b4e68c8": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HTMLModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_9185f86719af476da41e3835e8f06f8d",
+      "placeholder": "​",
+      "style": "IPY_MODEL_0b795d4b68014de19bf9579c67b55ffb",
+      "value": " 870/870 [05:35&lt;00:00,  2.59ex/s]"
+     }
+    },
+    "75e00c38605f44cfb584067db1160349": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "FloatProgressModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "FloatProgressModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "ProgressView",
+      "bar_style": "success",
+      "description": "100%",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_73ecbfc3c5c5456bb42e19b8a34b1576",
+      "max": 1,
+      "min": 0,
+      "orientation": "horizontal",
+      "style": "IPY_MODEL_c01aca3229a24d41841be2b4a3a65bcc",
+      "value": 1
+     }
+    },
+    "768ab09956774f50a79b2493a8bf179b": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "76d162d3ea0845cc837651a77a5a2d36": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HBoxModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HBoxModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HBoxView",
+      "box_style": "",
+      "children": [
+       "IPY_MODEL_f6b01ad0433a40178ef3ba5657bc1583",
+       "IPY_MODEL_eed2ccc12daa4c71b080794a7a18f5cb"
+      ],
+      "layout": "IPY_MODEL_98c594f1e41e4b3fab10f0763bd93d75"
+     }
+    },
+    "771959e46cb64b3ebafe931f96f5ff52": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HBoxModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HBoxModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HBoxView",
+      "box_style": "",
+      "children": [
+       "IPY_MODEL_f792530a76ee486688cbc2502dfae594",
+       "IPY_MODEL_d69468d63dd74fdd807fe061b92aa84e"
+      ],
+      "layout": "IPY_MODEL_0e999af234bd4b63ad2937e61d08b693"
+     }
+    },
+    "7916b06da182435a9cc1d13c73310500": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "7aa70322bdfe46938b583a20003093d5": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "DescriptionStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "DescriptionStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "description_width": ""
+     }
+    },
+    "7b4cfd2b448643b8a4409dd612aef0d1": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "7bf5b2b625764f63ad57a360c3fd0a61": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "DescriptionStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "DescriptionStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "description_width": ""
+     }
+    },
+    "7d62810674c8482abe46c60fc08884b4": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "ProgressStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "ProgressStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "bar_color": null,
+      "description_width": "initial"
+     }
+    },
+    "7e50f8027fb74d669daae5e46082026c": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "7edbecaccdd94ede8fddc0e1807e777e": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "FloatProgressModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "FloatProgressModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "ProgressView",
+      "bar_style": "success",
+      "description": "100%",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_3e3a022a9f304b0f9f7ef067fcee1e56",
+      "max": 3478,
+      "min": 0,
+      "orientation": "horizontal",
+      "style": "IPY_MODEL_b9c5c6dd54cc4dc5ad5a2bb69a24ab05",
+      "value": 3478
+     }
+    },
+    "7ef969e47c2d429a9848d5ab3f5bb2d9": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HBoxModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HBoxModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HBoxView",
+      "box_style": "",
+      "children": [
+       "IPY_MODEL_015c5690e1ea4281954c7efda1c80a6a",
+       "IPY_MODEL_f4135dd72864445391f43f387635bfdc"
+      ],
+      "layout": "IPY_MODEL_fe62265afdc74026b7e9c5a50ef61d2c"
+     }
+    },
+    "7f5203fde6b64bf7ad53d6ecd3041bfc": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "DescriptionStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "DescriptionStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "description_width": ""
+     }
+    },
+    "7f787df324514a8c915785e272a8af18": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "FloatProgressModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "FloatProgressModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "ProgressView",
+      "bar_style": "info",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_7916b06da182435a9cc1d13c73310500",
+      "max": 1,
+      "min": 0,
+      "orientation": "horizontal",
+      "style": "IPY_MODEL_71ffdf6f26ba4381a8e671958e679f88",
+      "value": 1
+     }
+    },
+    "80697300a4394b909f1c499ba80aeb13": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "813fc95246034f5cb9e5198897b4ed42": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "DescriptionStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "DescriptionStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "description_width": ""
+     }
+    },
+    "82015055d32449b89346ea18e7474c4d": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HBoxModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HBoxModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HBoxView",
+      "box_style": "",
+      "children": [
+       "IPY_MODEL_f5f1f0865d7e4d8b810ccb9c3c4d2683",
+       "IPY_MODEL_416badb151ee4660b53fdbc136e0c8fb"
+      ],
+      "layout": "IPY_MODEL_a170c0cb21cf425fbee97fd6d5584e2c"
+     }
+    },
+    "824569c63ec445c08362659ca228dd2a": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "DescriptionStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "DescriptionStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "description_width": ""
+     }
+    },
+    "8292dafcd40745958d0f3c563bf6b9b0": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "ProgressStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "ProgressStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "bar_color": null,
+      "description_width": "initial"
+     }
+    },
+    "83b51e16d88046c48dcd745cf09d2e56": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "84e7f0001ebe458dad3c96e7e9a38cdc": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "8701fb161cec47e89fc4d57b599ee7fe": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HBoxModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HBoxModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HBoxView",
+      "box_style": "",
+      "children": [
+       "IPY_MODEL_7f787df324514a8c915785e272a8af18",
+       "IPY_MODEL_889da3e5ed2945849d3c8a6a75175747"
+      ],
+      "layout": "IPY_MODEL_1813458f75514f039ba0214597a09bb4"
+     }
+    },
+    "889da3e5ed2945849d3c8a6a75175747": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HTMLModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_2cd13e03a2ab45dc8570c8c739a613b4",
+      "placeholder": "​",
+      "style": "IPY_MODEL_59e0f5200068461cbfb256ad5479c4c8",
+      "value": " 1647/0 [00:00&lt;00:00, 14767.90 examples/s]"
+     }
+    },
+    "8ad3e4b211e34c048d0f48e36fdbfe48": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "DescriptionStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "DescriptionStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "description_width": ""
+     }
+    },
+    "8bb78a89ff81400791e3005098fdcb94": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "8c07a528fc4a4e108b393ab117fe2e46": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HTMLModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_8bb78a89ff81400791e3005098fdcb94",
+      "placeholder": "​",
+      "style": "IPY_MODEL_813fc95246034f5cb9e5198897b4ed42",
+      "value": " 1/1 [00:00&lt;00:00, 13.94ba/s]"
+     }
+    },
+    "8d409ca0372a48e2972ca1d8eee5ffa1": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HTMLModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_b0479f03f96241ca959f6fe7bcbd1aba",
+      "placeholder": "​",
+      "style": "IPY_MODEL_d362345c05234c97a675c6bacdad0e92",
+      "value": " 1647/1647 [01:20&lt;00:00, 20.38ex/s]"
+     }
+    },
+    "8dd5b08bb5bd4e608d04122424796ae7": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HTMLModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_9eb51a6ecf3f41578aa397a5c2a33673",
+      "placeholder": "​",
+      "style": "IPY_MODEL_2f18d89c684343b69c3f44ffbb9b42a0",
+      "value": " 1726/0 [00:00&lt;00:00, 13986.88 examples/s]"
+     }
+    },
+    "8dddd0245dcb4532917cbfa0181d2a00": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "FloatProgressModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "FloatProgressModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "ProgressView",
+      "bar_style": "success",
+      "description": "#2: 100%",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_b1d93a7521fa47b8a815445b5232da59",
+      "max": 412,
+      "min": 0,
+      "orientation": "horizontal",
+      "style": "IPY_MODEL_024989cea06f435894776b0a921164b2",
+      "value": 412
+     }
+    },
+    "8df9d19602cb4951b397c385458a11ef": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "DescriptionStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "DescriptionStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "description_width": ""
+     }
+    },
+    "8e1a85a4a6214a16b7431da23a301ada": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "FloatProgressModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "FloatProgressModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "ProgressView",
+      "bar_style": "success",
+      "description": "Downloading: ",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_d453bd4a35e54bfba20dac1fe86c60c1",
+      "max": 1764,
+      "min": 0,
+      "orientation": "horizontal",
+      "style": "IPY_MODEL_a3c04c75ec9743feb795f69e7c4dff4f",
+      "value": 1764
+     }
+    },
+    "8e63ba7f1fd24555bf11bc9dbe9c770b": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HTMLModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_26e7bab0f3bf4797bfcef83dcace24f0",
+      "placeholder": "​",
+      "style": "IPY_MODEL_405b5de4ae854cf9896f63d15f2207dd",
+      "value": " 52/52 [00:30&lt;00:00,  1.68ba/s]"
+     }
+    },
+    "8f737725708c4097a8caaf4da6229636": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "90b8bc59e26a46009e1d3763f86f227a": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HBoxModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HBoxModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HBoxView",
+      "box_style": "",
+      "children": [
+       "IPY_MODEL_98e7ab5f7ebf426fbb71a37bbad4c28f",
+       "IPY_MODEL_e3b719c0ffcc4fd1b410ffb7f969b7a5"
+      ],
+      "layout": "IPY_MODEL_3e2cd59ac697495f8db14b894b783f95"
+     }
+    },
+    "9185f86719af476da41e3835e8f06f8d": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "91fcf0641fe3489ab96f3aaa40adf245": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "923ed9e127524187ab8cfcac31164ba7": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "929cde17b3484f3e9e8f8774bc43e374": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "ProgressStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "ProgressStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "bar_color": null,
+      "description_width": "initial"
+     }
+    },
+    "92a35db69bbf4ad6af44c53aa3870be5": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HBoxModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HBoxModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HBoxView",
+      "box_style": "",
+      "children": [
+       "IPY_MODEL_b94e374d92c146009447c3827b977267",
+       "IPY_MODEL_1f1faa7b986e475c9e6839b2e7b55c74"
+      ],
+      "layout": "IPY_MODEL_389e43e47a734193a507817ebad955f7"
+     }
+    },
+    "93f191a48b3141e1889fd94870b6ac0e": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "9532db4cdc5e4371a4a02055a4c67a08": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "DescriptionStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "DescriptionStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "description_width": ""
+     }
+    },
+    "969080b52ad44ee997829986d198c505": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "DescriptionStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "DescriptionStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "description_width": ""
+     }
+    },
+    "98c594f1e41e4b3fab10f0763bd93d75": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "98e7ab5f7ebf426fbb71a37bbad4c28f": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "FloatProgressModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "FloatProgressModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "ProgressView",
+      "bar_style": "info",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_2f5406546970425282a881b5d2f7c248",
+      "max": 1,
+      "min": 0,
+      "orientation": "horizontal",
+      "style": "IPY_MODEL_4382726ef043441a9b1a4a647d84f242",
+      "value": 1
+     }
+    },
+    "998676d59f9c464e8463d65baad6448b": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HTMLModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_7b4cfd2b448643b8a4409dd612aef0d1",
+      "placeholder": "​",
+      "style": "IPY_MODEL_7bf5b2b625764f63ad57a360c3fd0a61",
+      "value": " 1647/1647 [00:45&lt;00:00, 36.39ex/s]"
+     }
+    },
+    "99d5c44ea54b45ee9bd89380cb1ad189": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "9eb51a6ecf3f41578aa397a5c2a33673": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "9f79629ad6a94201acf3283862d1ae17": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "DescriptionStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "DescriptionStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "description_width": ""
+     }
+    },
+    "9fee9d9dd1164d97a9109e942444c332": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HTMLModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_c126ea97019149848396e593cfab016f",
+      "placeholder": "​",
+      "style": "IPY_MODEL_f9efaa7678c2450f847ff2c2f21ff96e",
+      "value": " 52/52 [00:31&lt;00:00,  1.66ba/s]"
+     }
+    },
+    "a170c0cb21cf425fbee97fd6d5584e2c": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "a34dae18d9994b848630d4e3d836e0cb": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "a3c04c75ec9743feb795f69e7c4dff4f": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "ProgressStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "ProgressStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "bar_color": null,
+      "description_width": "initial"
+     }
+    },
+    "a47f1ea64f894f0b8e6b277c31ae9f7d": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "ProgressStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "ProgressStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "bar_color": null,
+      "description_width": "initial"
+     }
+    },
+    "a58c203a7cc54086aea45f2029821207": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "FloatProgressModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "FloatProgressModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "ProgressView",
+      "bar_style": "success",
+      "description": "100%",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_b1b6a4649fc34c9996f993c57671766b",
+      "max": 1647,
+      "min": 0,
+      "orientation": "horizontal",
+      "style": "IPY_MODEL_c8fdf261ac294093a355778a3a4aba3b",
+      "value": 1647
+     }
+    },
+    "a868dea9d9b047a4b853b390e138e4c1": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "aafd4b2c56db43378c4627797665db17": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HTMLModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_ad428686450f4ebdb50a0356b2e5a8c4",
+      "placeholder": "​",
+      "style": "IPY_MODEL_ccb720bf256e42f7b0251494ccb7741f",
+      "value": " 1/1 [00:45&lt;00:00, 45.03s/ba]"
+     }
+    },
+    "ab72c80dfd5e4ab19a183f4204486b59": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "DescriptionStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "DescriptionStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "description_width": ""
+     }
+    },
+    "ac35dca0845149a284b9867d9e607232": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HBoxModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HBoxModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HBoxView",
+      "box_style": "",
+      "children": [
+       "IPY_MODEL_5071a31d06f544a5b7340a4e863d8fdf",
+       "IPY_MODEL_542027ba12f444d586e8072452badea0"
+      ],
+      "layout": "IPY_MODEL_b54bff6261964119bcb562c1a9f74ce6"
+     }
+    },
+    "ad428686450f4ebdb50a0356b2e5a8c4": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "af85713f677243d19cba9fe69a4a5f46": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "b0479f03f96241ca959f6fe7bcbd1aba": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "b054b00a32e64fc5988fbd2966ebbce6": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "b0e3a36279d243ab9943149705c72c3e": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "FloatProgressModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "FloatProgressModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "ProgressView",
+      "bar_style": "success",
+      "description": "Downloading: ",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_a34dae18d9994b848630d4e3d836e0cb",
+      "max": 5925,
+      "min": 0,
+      "orientation": "horizontal",
+      "style": "IPY_MODEL_530f66ac087e4f8f979fcaa33941c60d",
+      "value": 5925
+     }
+    },
+    "b0f3a205ad4546188fc6e7e7cf96ab32": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "ProgressStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "ProgressStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "bar_color": null,
+      "description_width": "initial"
+     }
+    },
+    "b177a8cb85a24b88ab6d56205b630f1d": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "b1b6a4649fc34c9996f993c57671766b": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "b1d93a7521fa47b8a815445b5232da59": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "b2473405490e4556bf30c0cc81237aa5": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "b320306eaf264ad9872d507a1a1cb2da": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "b54bff6261964119bcb562c1a9f74ce6": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "b6221b4c04e64c9da9eb9e11539bac89": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HBoxModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HBoxModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HBoxView",
+      "box_style": "",
+      "children": [
+       "IPY_MODEL_02d1f77324854fbca0df9384c57faac8",
+       "IPY_MODEL_8e63ba7f1fd24555bf11bc9dbe9c770b"
+      ],
+      "layout": "IPY_MODEL_dc6862530f6e429ba61a169b4c95722c"
+     }
+    },
+    "b78413dcc0584a0c8f71731a06aaa1b8": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "b7c43fb5efdd4afbb82c81b923f2815a": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HBoxModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HBoxModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HBoxView",
+      "box_style": "",
+      "children": [
+       "IPY_MODEL_8dddd0245dcb4532917cbfa0181d2a00",
+       "IPY_MODEL_3bdb4058f40f40e3a10e323325a64638"
+      ],
+      "layout": "IPY_MODEL_c0a661f20e7e4649a3c8c42a5fd01956"
+     }
+    },
+    "b94e374d92c146009447c3827b977267": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "FloatProgressModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "FloatProgressModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "ProgressView",
+      "bar_style": "success",
+      "description": "100%",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_b177a8cb85a24b88ab6d56205b630f1d",
+      "max": 3478,
+      "min": 0,
+      "orientation": "horizontal",
+      "style": "IPY_MODEL_4ff7ccffc36a4a0f93031f5cdc3b718d",
+      "value": 3478
+     }
+    },
+    "b9c5c6dd54cc4dc5ad5a2bb69a24ab05": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "ProgressStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "ProgressStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "bar_color": null,
+      "description_width": "initial"
+     }
+    },
+    "bc41384bbae04044b9780651c6b5a47c": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "bd0958ea97b141b1aca367c71721c549": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HBoxModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HBoxModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HBoxView",
+      "box_style": "",
+      "children": [
+       "IPY_MODEL_d080668299ef42fabb8ab6fbcf329cea",
+       "IPY_MODEL_aafd4b2c56db43378c4627797665db17"
+      ],
+      "layout": "IPY_MODEL_0354ab33471e4c34a0c1b3c062bcd6bb"
+     }
+    },
+    "bd187486ac2548f2961cfcb63d852de1": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "FloatProgressModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "FloatProgressModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "ProgressView",
+      "bar_style": "success",
+      "description": "#1: 100%",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_58f3e8002f984594ac05c973aa78ef69",
+      "max": 52,
+      "min": 0,
+      "orientation": "horizontal",
+      "style": "IPY_MODEL_231c66f195d34f86b216805518f4bccd",
+      "value": 52
+     }
+    },
+    "bd3447291ce54812af10ac6245ea4328": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "beca070c32124a119a08cb21c2ca95e5": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "ProgressStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "ProgressStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "bar_color": null,
+      "description_width": "initial"
+     }
+    },
+    "bee0f50055eb4f738636142a10da0ddd": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "bf9e57d81135412d9a9a2281f28bd52a": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HBoxModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HBoxModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HBoxView",
+      "box_style": "",
+      "children": [
+       "IPY_MODEL_579b6055028f473981ce789a0733a753",
+       "IPY_MODEL_4fb7347e9ca542e6ab9003bf4db218e0"
+      ],
+      "layout": "IPY_MODEL_c41610c0baef412984f8661d96e08b7e"
+     }
+    },
+    "c01aca3229a24d41841be2b4a3a65bcc": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "ProgressStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "ProgressStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "bar_color": null,
+      "description_width": "initial"
+     }
+    },
+    "c0a661f20e7e4649a3c8c42a5fd01956": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "c0e6b6e6395d4dbd827eb1c0de1ad21a": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "c126ea97019149848396e593cfab016f": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "c41610c0baef412984f8661d96e08b7e": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "c546bca23ee248a1be7bd8ead3e82a8f": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "ProgressStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "ProgressStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "bar_color": null,
+      "description_width": "initial"
+     }
+    },
+    "c8fdf261ac294093a355778a3a4aba3b": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "ProgressStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "ProgressStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "bar_color": null,
+      "description_width": "initial"
+     }
+    },
+    "c9dc4421940241c59f1151aeabedc98b": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "cb5666eb8ebb4d1392e98d6b5af8761c": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "DescriptionStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "DescriptionStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "description_width": ""
+     }
+    },
+    "cc9c1e00c2d34516b8fd9edff96bb0d8": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HBoxModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HBoxModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HBoxView",
+      "box_style": "",
+      "children": [
+       "IPY_MODEL_33c92b5afd1d4b6d88016aabfb434194",
+       "IPY_MODEL_998676d59f9c464e8463d65baad6448b"
+      ],
+      "layout": "IPY_MODEL_6abfbe44a1bd4518b41f5f53f920e936"
+     }
+    },
+    "ccb720bf256e42f7b0251494ccb7741f": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "DescriptionStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "DescriptionStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "description_width": ""
+     }
+    },
+    "ce337f50183942e6a74ca1b33735ade9": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HTMLModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_e9a702f10538415b970ea1345804d72c",
+      "placeholder": "​",
+      "style": "IPY_MODEL_9532db4cdc5e4371a4a02055a4c67a08",
+      "value": " 23.0k/? [00:00&lt;00:00, 72.2kB/s]"
+     }
+    },
+    "ceb44ba4fdf34da19a52469acf1ce63f": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "d080668299ef42fabb8ab6fbcf329cea": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "FloatProgressModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "FloatProgressModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "ProgressView",
+      "bar_style": "success",
+      "description": "100%",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_f972527479e74337a98f236ed018ae1d",
+      "max": 1,
+      "min": 0,
+      "orientation": "horizontal",
+      "style": "IPY_MODEL_b0f3a205ad4546188fc6e7e7cf96ab32",
+      "value": 1
+     }
+    },
+    "d35c15beeb33476894b07c3563f8facd": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "DescriptionStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "DescriptionStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "description_width": ""
+     }
+    },
+    "d362345c05234c97a675c6bacdad0e92": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "DescriptionStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "DescriptionStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "description_width": ""
+     }
+    },
+    "d453bd4a35e54bfba20dac1fe86c60c1": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "d4a3f79644fc41848450ba29e6fdfc3d": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "d5fb02debe4347e781543a996ce39be3": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HBoxModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HBoxModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HBoxView",
+      "box_style": "",
+      "children": [
+       "IPY_MODEL_8e1a85a4a6214a16b7431da23a301ada",
+       "IPY_MODEL_57198e3250374e1fa64c5a4be255861e"
+      ],
+      "layout": "IPY_MODEL_da12267c52144292adb9896249d61a6a"
+     }
+    },
+    "d649c0f9c1c24634a84b7ef697721ffa": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "d69468d63dd74fdd807fe061b92aa84e": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HTMLModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_84e7f0001ebe458dad3c96e7e9a38cdc",
+      "placeholder": "​",
+      "style": "IPY_MODEL_7f5203fde6b64bf7ad53d6ecd3041bfc",
+      "value": " 869/869 [05:47&lt;00:00,  2.50ex/s]"
+     }
+    },
+    "d7f27e9cf8a844349ca90393e0c49a03": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "d96e01ad62c342cdb7d9b1eceb39afa3": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HBoxModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HBoxModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HBoxView",
+      "box_style": "",
+      "children": [
+       "IPY_MODEL_e6178f7b148c4bf39f2826f208e0cc64",
+       "IPY_MODEL_f78ff14b9c8f46448ed1ecb3fe1f5e0b"
+      ],
+      "layout": "IPY_MODEL_e6ce9330460d4a0fb67cc493ca74ae96"
+     }
+    },
+    "da12267c52144292adb9896249d61a6a": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "da1ff50f8b9241108a325ada04224642": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "ProgressStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "ProgressStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "bar_color": null,
+      "description_width": "initial"
+     }
+    },
+    "db71db50799c404aafa4a54de8b9b799": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "dc6862530f6e429ba61a169b4c95722c": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "dde7ae43ef954ef1b901c80f0a4e11fd": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "dec796237765477ea904834d9a824b61": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "def702d8f8354fa4999587a5c68d0034": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HBoxModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HBoxModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HBoxView",
+      "box_style": "",
+      "children": [
+       "IPY_MODEL_edf36819322e4f9fa227a11592fef429",
+       "IPY_MODEL_ce337f50183942e6a74ca1b33735ade9"
+      ],
+      "layout": "IPY_MODEL_2fd148d5587b4139919b0158f9dad71e"
+     }
+    },
+    "e273548a15aa4d4994132b317adb66fc": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "FloatProgressModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "FloatProgressModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "ProgressView",
+      "bar_style": "success",
+      "description": "#0: 100%",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_80697300a4394b909f1c499ba80aeb13",
+      "max": 52,
+      "min": 0,
+      "orientation": "horizontal",
+      "style": "IPY_MODEL_7d62810674c8482abe46c60fc08884b4",
+      "value": 52
+     }
+    },
+    "e3b719c0ffcc4fd1b410ffb7f969b7a5": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HTMLModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_c9dc4421940241c59f1151aeabedc98b",
+      "placeholder": "​",
+      "style": "IPY_MODEL_19e263785ea343ba99ee2127d9b83d1d",
+      "value": " 1831/0 [00:04&lt;00:00,  4.82s/ examples]"
+     }
+    },
+    "e51b5fd9d5a6416d986fac1526d1666f": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "e6178f7b148c4bf39f2826f208e0cc64": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "FloatProgressModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "FloatProgressModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "ProgressView",
+      "bar_style": "success",
+      "description": "#0: 100%",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_6ba6d07674a34836be53cf173c2b61ca",
+      "max": 412,
+      "min": 0,
+      "orientation": "horizontal",
+      "style": "IPY_MODEL_929cde17b3484f3e9e8f8774bc43e374",
+      "value": 412
+     }
+    },
+    "e6ce9330460d4a0fb67cc493ca74ae96": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "e9a702f10538415b970ea1345804d72c": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "ec36a94ee2574ac8b227ccaefdee5520": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "DescriptionStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "DescriptionStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "description_width": ""
+     }
+    },
+    "edf36819322e4f9fa227a11592fef429": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "FloatProgressModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "FloatProgressModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "ProgressView",
+      "bar_style": "success",
+      "description": "Downloading: ",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_93f191a48b3141e1889fd94870b6ac0e",
+      "max": 4662,
+      "min": 0,
+      "orientation": "horizontal",
+      "style": "IPY_MODEL_8292dafcd40745958d0f3c563bf6b9b0",
+      "value": 4662
+     }
+    },
+    "ee641bbf54a7499597713c517baa81bb": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HBoxModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HBoxModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HBoxView",
+      "box_style": "",
+      "children": [
+       "IPY_MODEL_4f8957dc035d4c1a9e8630fc8ab8cd10",
+       "IPY_MODEL_757e7bd0e6c5410da0490d191b4e68c8"
+      ],
+      "layout": "IPY_MODEL_3d929b9e2518402b81a71757ffb753d2"
+     }
+    },
+    "eed2ccc12daa4c71b080794a7a18f5cb": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HTMLModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_f18eddbd3d994ddc88f37e02d754c206",
+      "placeholder": "​",
+      "style": "IPY_MODEL_20347ed29fdc4c0a96da28c09aacf44d",
+      "value": " 870/870 [05:39&lt;00:00,  2.45ex/s]"
+     }
+    },
+    "f18eddbd3d994ddc88f37e02d754c206": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "f203c54e7e054d97aa4d1097f320f611": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "FloatProgressModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "FloatProgressModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "ProgressView",
+      "bar_style": "success",
+      "description": "#3: 100%",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_0cd1932178c945d48604ffd299e65d2c",
+      "max": 411,
+      "min": 0,
+      "orientation": "horizontal",
+      "style": "IPY_MODEL_3ec3285e9f3e4a5abcefabb7f140f4a3",
+      "value": 411
+     }
+    },
+    "f3905820a42c499fba04af9c1ad19705": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "FloatProgressModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "FloatProgressModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "ProgressView",
+      "bar_style": "success",
+      "description": "#2: 100%",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_fc9504846f424542a7feb932964f1f5b",
+      "max": 869,
+      "min": 0,
+      "orientation": "horizontal",
+      "style": "IPY_MODEL_4c0ad31e73234e46aac0a297ec18bdeb",
+      "value": 869
+     }
+    },
+    "f3adb92e618743cca3299e3e7b6e369f": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HBoxModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HBoxModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HBoxView",
+      "box_style": "",
+      "children": [
+       "IPY_MODEL_b0e3a36279d243ab9943149705c72c3e",
+       "IPY_MODEL_12696cc03f464a63a411efb2b5e5ac3b"
+      ],
+      "layout": "IPY_MODEL_83b51e16d88046c48dcd745cf09d2e56"
+     }
+    },
+    "f4135dd72864445391f43f387635bfdc": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HTMLModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_923ed9e127524187ab8cfcac31164ba7",
+      "placeholder": "​",
+      "style": "IPY_MODEL_8df9d19602cb4951b397c385458a11ef",
+      "value": " 109/109 [00:56&lt;00:00,  1.93ba/s]"
+     }
+    },
+    "f57d087016124ebeb073fd7428dcb68b": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "f5f1f0865d7e4d8b810ccb9c3c4d2683": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "FloatProgressModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "FloatProgressModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "ProgressView",
+      "bar_style": "success",
+      "description": "#1: 100%",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_e51b5fd9d5a6416d986fac1526d1666f",
+      "max": 412,
+      "min": 0,
+      "orientation": "horizontal",
+      "style": "IPY_MODEL_a47f1ea64f894f0b8e6b277c31ae9f7d",
+      "value": 412
+     }
+    },
+    "f6930dd5519d4dfda64c597def220a30": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HTMLModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_56ad6231a0a04228be29ceecbc6b7c0e",
+      "placeholder": "​",
+      "style": "IPY_MODEL_ab72c80dfd5e4ab19a183f4204486b59",
+      "value": " 52/52 [00:31&lt;00:00,  1.63ba/s]"
+     }
+    },
+    "f6b01ad0433a40178ef3ba5657bc1583": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "FloatProgressModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "FloatProgressModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "ProgressView",
+      "bar_style": "success",
+      "description": "#0: 100%",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_69828f4a101f4340916a4be141866904",
+      "max": 870,
+      "min": 0,
+      "orientation": "horizontal",
+      "style": "IPY_MODEL_beca070c32124a119a08cb21c2ca95e5",
+      "value": 870
+     }
+    },
+    "f78ff14b9c8f46448ed1ecb3fe1f5e0b": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "HTMLModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_b054b00a32e64fc5988fbd2966ebbce6",
+      "placeholder": "​",
+      "style": "IPY_MODEL_5a5bc8b4a1c644dea08a60128d888d10",
+      "value": " 412/412 [03:06&lt;00:00,  2.20ex/s]"
+     }
+    },
+    "f792530a76ee486688cbc2502dfae594": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "FloatProgressModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "FloatProgressModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "ProgressView",
+      "bar_style": "success",
+      "description": "#3: 100%",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_7e50f8027fb74d669daae5e46082026c",
+      "max": 869,
+      "min": 0,
+      "orientation": "horizontal",
+      "style": "IPY_MODEL_1261590ef796493798f7068ea0547b74",
+      "value": 869
+     }
+    },
+    "f972527479e74337a98f236ed018ae1d": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "f9efaa7678c2450f847ff2c2f21ff96e": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "DescriptionStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "DescriptionStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "description_width": ""
+     }
+    },
+    "fa7926bbe77e48b3a0648b45f5d2dc7a": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_name": "ProgressStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "ProgressStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "bar_color": null,
+      "description_width": "initial"
+     }
+    },
+    "fc9504846f424542a7feb932964f1f5b": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "fe62265afdc74026b7e9c5a50ef61d2c": {
+     "model_module": "@jupyter-widgets/base",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    }
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}