update model card README.md

README.md

@@ -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: 3.0665
-- Wer: 1.0
+- Loss: 1.2368
+- Wer: 0.8655
 
 ## Model description
 
@@ -34,7 +34,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
+- learning_rate: 1e-05
 - train_batch_size: 32
 - eval_batch_size: 8
 - seed: 42
@@ -46,15 +46,15 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Wer |
-|:-------------:|:-----:|:----:|:---------------:|:---:|
-| 6.467         | 4.0   | 500  | 3.1080          | 1.0 |
-| 3.153         | 8.0   | 1000 | 3.0003          | 1.0 |
-| 3.092         | 12.0  | 1500 | 2.9949          | 1.0 |
-| 3.0631        | 16.0  | 2000 | 3.0851          | 1.0 |
-| 3.0475        | 20.0  | 2500 | 3.0497          | 1.0 |
-| 3.0552        | 24.0  | 3000 | 3.0839          | 1.0 |
-| 3.0351        | 28.0  | 3500 | 3.0665          | 1.0 |
+| Training Loss | Epoch | Step | Validation Loss | Wer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 10.7111       | 4.0   | 500  | 6.1429          | 1.0    |
+| 4.8905        | 8.0   | 1000 | 6.0597          | 1.0    |
+| 3.4516        | 12.0  | 1500 | 3.0125          | 1.0    |
+| 2.9895        | 16.0  | 2000 | 2.9629          | 1.0    |
+| 2.9155        | 20.0  | 2500 | 2.4479          | 1.0    |
+| 2.3186        | 24.0  | 3000 | 1.5888          | 0.9565 |
+| 1.8469        | 28.0  | 3500 | 1.2368          | 0.8655 |
 
 
 ### Framework versions