End of training

README.md

@@ -5,24 +5,9 @@ tags:
 - generated_from_trainer
 datasets:
 - common_voice_6_1
-metrics:
-- wer
 model-index:
 - name: wav2vec2-large-mms-1b-turkish-colab
-  results:
-  - task:
-      name: Automatic Speech Recognition
-      type: automatic-speech-recognition
-    dataset:
-      name: common_voice_6_1
-      type: common_voice_6_1
-      config: tr
-      split: test
-      args: tr
-    metrics:
-    - name: Wer
-      type: wer
-      value: 0.9835563272393014
+  results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,9 +16,6 @@ should probably proofread and complete it, then remove this comment. -->
 # wav2vec2-large-mms-1b-turkish-colab
 
 This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the common_voice_6_1 dataset.
-It achieves the following results on the evaluation set:
-- Loss: 2.4395
-- Wer: 0.9836
 
 ## Model description
 
@@ -53,7 +35,7 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.001
-- train_batch_size: 16
+- train_batch_size: 32
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
@@ -61,23 +43,9 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_steps: 100
 - num_epochs: 4
 
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Wer    |
-|:-------------:|:-----:|:----:|:---------------:|:------:|
-| 6.2025        | 0.46  | 100  | 5.8610          | 1.0478 |
-| 3.2809        | 0.92  | 200  | 3.5010          | 1.0029 |
-| 3.0173        | 1.38  | 300  | 3.2271          | 0.9990 |
-| 2.8897        | 1.83  | 400  | 3.4469          | 0.9981 |
-| 2.8081        | 2.29  | 500  | 3.1375          | 1.0044 |
-| 2.7393        | 2.75  | 600  | 2.6899          | 0.9948 |
-| 2.5172        | 3.21  | 700  | 2.7153          | 0.9949 |
-| 2.4154        | 3.67  | 800  | 2.4395          | 0.9836 |
-
-
 ### Framework versions
 
-- Transformers 4.33.0.dev0
+- Transformers 4.33.0
 - Pytorch 2.0.1+cu117
 - Datasets 2.14.4
 - Tokenizers 0.13.3

adapter.tur.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed8fe2f53c5d0fde0f80ab677ff86415aaf26efae3d6c4182db8f89ea69c1c3c
-size 8839532
+oid sha256:a49adfac4de6cf5b45e2655e80419d4bb6d3d32f6ab057457df5504620d421a1
+size 9054748

config.json

@@ -77,7 +77,7 @@
   "num_hidden_layers": 48,
   "num_negatives": 100,
   "output_hidden_size": 1280,
-  "pad_token_id": 36,
+  "pad_token_id": 1,
   "proj_codevector_dim": 1024,
   "tdnn_dilation": [
     1,
@@ -101,8 +101,8 @@
     1
   ],
   "torch_dtype": "float32",
-  "transformers_version": "4.33.0.dev0",
+  "transformers_version": "4.33.0",
   "use_weighted_layer_sum": false,
-  "vocab_size": 39,
+  "vocab_size": 81,
   "xvector_output_dim": 512
 }

preprocessor_config.json

@@ -1,9 +1,19 @@
 {
-  "do_normalize": true,
-  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "do_normalize": false,
+  "feature_extractor_type": "SpeechT5FeatureExtractor",
   "feature_size": 1,
+  "fmax": 7600,
+  "fmin": 80,
+  "frame_signal_scale": 1.0,
+  "hop_length": 16,
+  "mel_floor": 1e-10,
+  "num_mel_bins": 80,
   "padding_side": "right",
   "padding_value": 0.0,
+  "processor_class": "SpeechT5Processor",
+  "reduction_factor": 2,
   "return_attention_mask": true,
-  "sampling_rate": 16000
+  "sampling_rate": 16000,
+  "win_function": "hann_window",
+  "win_length": 64
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:418bde28a3118f67f989b961834588c31b54e42ca8b5ad9145e1aafed71873db
-size 3859175565
+oid sha256:81b70144e8d7d8e190d4c93638e620240fc471b846cf31375d90355a3e4560f2
+size 3859390797

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:972d6512832df904da66bfd304b32c108f74762499b024eee235dcf47022f660
+oid sha256:26fca2f44571a70125f2ca7e5b4adfa4707bebf6ae2fe41b1963fc2b6a968433
 size 4091