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](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 21.0555
-- Wer: 1.4390
+- Loss: 28.7224
+- Wer: 1.0
 
 ## Model description
 
@@ -41,16 +41,18 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 3
+- num_epochs: 5
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Wer    |
-|:-------------:|:-----:|:----:|:---------------:|:------:|
-| No log        | 1.0   | 2    | 21.0555         | 1.4390 |
-| No log        | 2.0   | 4    | 21.0555         | 1.4390 |
-| No log        | 3.0   | 6    | 21.0555         | 1.4390 |
+| Training Loss | Epoch | Step | Validation Loss | Wer |
+|:-------------:|:-----:|:----:|:---------------:|:---:|
+| No log        | 1.0   | 2    | 28.7224         | 1.0 |
+| No log        | 2.0   | 4    | 28.7224         | 1.0 |
+| No log        | 3.0   | 6    | 28.7224         | 1.0 |
+| No log        | 4.0   | 8    | 28.7224         | 1.0 |
+| 57.4237       | 5.0   | 10   | 28.7224         | 1.0 |
 
 
 ### Framework versions