Upload 9 files

README.md

@@ -0,0 +1,89 @@
+---
+base_model: facebook/w2v-bert-2.0
+library_name: transformers
+language: 
+  - uk
+license: "apache-2.0"
+tags:
+- automatic-speech-recognition
+datasets:
+  - espnet/yodas2
+metrics:
+  - wer
+model-index:
+  - name: w2v-bert-uk-v2.1
+    results:
+      - task:
+          name: Automatic Speech Recognition
+          type: automatic-speech-recognition
+        dataset:
+          name: common_voice_10_0
+          type: common_voice_10_0
+          config: uk
+          split: test
+          args: uk
+        metrics:
+          - name: Wer
+            type: wer
+            value: 0.0000
+---
+
+# w2v-bert-uk `v2.1`
+
+
+## Community
+
+- **Discord**: https://bit.ly/discord-uds
+- Speech Recognition: https://t.me/speech_recognition_uk
+- Speech Synthesis: https://t.me/speech_synthesis_uk
+
+## Overview
+
+This is a next model of https://huggingface.co/Yehor/w2v-bert-uk
+
+## Demo
+
+Use https://huggingface.co/spaces/Yehor/w2v-bert-uk-v2.1-demo space to see how the model works with your audios.
+
+## Usage
+
+```python
+# pip install -U torch soundfile transformers
+
+import torch
+import soundfile as sf
+from transformers import AutoModelForCTC, Wav2Vec2BertProcessor
+
+# Config
+model_name = 'Yehor/w2v-bert-2.0-uk-v2.1'
+device = 'cuda:1' # or cpu
+sampling_rate = 16_000
+
+# Load the model
+asr_model = AutoModelForCTC.from_pretrained(model_name).to(device)
+processor = Wav2Vec2BertProcessor.from_pretrained(model_name)
+
+paths = [
+  'sample1.wav',
+]
+
+# Extract audio
+audio_inputs = []
+for path in paths:
+  audio_input, _ = sf.read(path)
+  audio_inputs.append(audio_input)
+
+# Transcribe the audio
+inputs = processor(audio_inputs, sampling_rate=sampling_rate).input_features
+features = torch.tensor(inputs).to(device)
+
+with torch.inference_mode():
+  logits = asr_model(features).logits
+
+predicted_ids = torch.argmax(logits, dim=-1)
+predictions = processor.batch_decode(predicted_ids)
+
+# Log results
+print('Predictions:')
+print(predictions)
+```

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 38,
+  "<s>": 37
+}

alphabet.json

@@ -0,0 +1 @@
+{"labels": ["'", "", "\u2047", " ", "\u0430", "\u0431", "\u0432", "\u0433", "\u0434", "\u0435", "\u0436", "\u0437", "\u0438", "\u0439", "\u043a", "\u043b", "\u043c", "\u043d", "\u043e", "\u043f", "\u0440", "\u0441", "\u0442", "\u0443", "\u0444", "\u0445", "\u0446", "\u0447", "\u0448", "\u0449", "\u044c", "\u044e", "\u044f", "\u0454", "\u0456", "\u0457", "\u0491", "<s>", "</s>"], "is_bpe": false}

config.json

@@ -0,0 +1,82 @@
+{
+  "_name_or_path": "facebook/w2v-bert-2.0",
+  "activation_dropout": 0.05,
+  "adapter_act": "relu",
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": true,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2BertForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_proj_size": 768,
+  "codevector_dim": 768,
+  "conformer_conv_dropout": 0.1,
+  "contrastive_logits_temperature": 0.1,
+  "conv_depthwise_kernel_size": 31,
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": true,
+  "diversity_loss_weight": 0.1,
+  "eos_token_id": 2,
+  "feat_proj_dropout": 0.05,
+  "feat_quantizer_dropout": 0.0,
+  "feature_projection_input_dim": 160,
+  "final_dropout": 0.0,
+  "hidden_act": "swish",
+  "hidden_dropout": 0.05,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "left_max_position_embeddings": 64,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.15,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "max_source_positions": 5000,
+  "model_type": "wav2vec2-bert",
+  "num_adapter_layers": 1,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 1,
+  "position_embeddings_type": "relative_key",
+  "proj_codevector_dim": 768,
+  "right_max_position_embeddings": 8,
+  "rotary_embedding_base": 10000,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.43.3",
+  "use_intermediate_ffn_before_adapter": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 39,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9da62ad9ef6b9eab87eb8f9386a1b3ec919d533bab6183ab00bfa6b046c4f40
+size 729088

preprocessor_config.json

@@ -0,0 +1,11 @@
+{
+  "feature_extractor_type": "SeamlessM4TFeatureExtractor",
+  "feature_size": 80,
+  "num_mel_bins": 80,
+  "padding_side": "right",
+  "padding_value": 1,
+  "processor_class": "Wav2Vec2ProcessorWithLM",
+  "return_attention_mask": true,
+  "sampling_rate": 16000,
+  "stride": 2
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "added_tokens_decoder": {
+    "1": {
+      "content": "<pad>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "2": {
+      "content": "<unk>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "37": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "38": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "processor_class": "Wav2Vec2ProcessorWithLM",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "<unk>",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,39 @@
+{
+  "'": 0,
+  "<pad>": 1,
+  "<unk>": 2,
+  "|": 3,
+  "а": 4,
+  "б": 5,
+  "в": 6,
+  "г": 7,
+  "д": 8,
+  "е": 9,
+  "ж": 10,
+  "з": 11,
+  "и": 12,
+  "й": 13,
+  "к": 14,
+  "л": 15,
+  "м": 16,
+  "н": 17,
+  "о": 18,
+  "п": 19,
+  "р": 20,
+  "с": 21,
+  "т": 22,
+  "у": 23,
+  "ф": 24,
+  "х": 25,
+  "ц": 26,
+  "ч": 27,
+  "ш": 28,
+  "щ": 29,
+  "ь": 30,
+  "ю": 31,
+  "я": 32,
+  "є": 33,
+  "і": 34,
+  "ї": 35,
+  "ґ": 36
+}