huyue012
/

wav2vec2-base-cynthia-tedlium-2500-v2

Automatic Speech Recognition Transformers PyTorch TensorBoard wav2vec2 generated_from_trainer Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

huyue012 commited on Nov 19, 2021

Commit

aaf373f

•

1 Parent(s): fe98d6b

update model card README.md

Files changed (1) hide show

README.md +11 -13

README.md CHANGED Viewed

@@ -14,8 +14,8 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6376
-- Wer: 0.2137
 ## Model description
@@ -34,7 +34,7 @@ More information needed
 ### Training hyperparameters
 The following hyperparameters were used during training:
-- learning_rate: 0.0005
 - train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
@@ -42,7 +42,7 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 500
 - num_epochs: 50
 - mixed_precision_training: Native AMP
@@ -50,15 +50,13 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 0.7233        | 5.26  | 400  | 5.6115          | 0.4909 |
-| 0.7224        | 10.52 | 800  | 1.1835          | 0.3629 |
-| 0.5193        | 15.78 | 1200 | 0.5786          | 0.2994 |
-| 0.4114        | 21.05 | 1600 | 0.6535          | 0.2823 |
-| 0.3279        | 26.31 | 2000 | 0.6783          | 0.2709 |
-| 0.2711        | 31.58 | 2400 | 0.6570          | 0.2490 |
-| 0.2776        | 36.84 | 2800 | 0.6724          | 0.2358 |
-| 0.1805        | 42.1  | 3200 | 0.6212          | 0.2241 |
-| 0.1535        | 47.37 | 3600 | 0.6376          | 0.2137 |
 ### Framework versions

 This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.6425
+- Wer: 0.2033
 ## Model description
 ### Training hyperparameters
 The following hyperparameters were used during training:
+- learning_rate: 0.0001
 - train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
 - total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1000
 - num_epochs: 50
 - mixed_precision_training: Native AMP
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
+| 0.1196        | 6.58  | 500  | 0.6498          | 0.2103 |
+| 0.1176        | 13.16 | 1000 | 0.6490          | 0.2169 |
+| 0.1227        | 19.73 | 1500 | 0.6241          | 0.2127 |
+| 0.1078        | 26.31 | 2000 | 0.6359          | 0.2118 |
+| 0.0956        | 32.89 | 2500 | 0.6330          | 0.2073 |
+| 0.1008        | 39.47 | 3000 | 0.6816          | 0.2036 |
+| 0.09          | 46.05 | 3500 | 0.6425          | 0.2033 |
 ### Framework versions