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: 1.1437
-- Wer: 0.5533
+- Loss: 1.6207
+- Wer: 0.5439
 
 ## Model description
 
@@ -48,9 +48,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 4.4131        | 8.93  | 500  | 2.9852          | 1.0    |
-| 2.347         | 17.86 | 1000 | 1.3474          | 0.8105 |
-| 0.7817        | 26.79 | 1500 | 1.1437          | 0.5533 |
+| 4.0857        | 5.88  | 500  | 2.8697          | 0.9996 |
+| 1.6315        | 11.76 | 1000 | 1.3319          | 0.7270 |
+| 0.7533        | 17.65 | 1500 | 1.3519          | 0.6263 |
+| 0.4383        | 23.53 | 2000 | 1.6394          | 0.5557 |
+| 0.2845        | 29.41 | 2500 | 1.6207          | 0.5439 |
 
 
 ### Framework versions