update model card README.md

README.md

@@ -14,7 +14,7 @@ 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: 6.3653
+- Loss: 2.9854
 - Wer: 1.0
 
 ## Model description
@@ -48,9 +48,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer |
 |:-------------:|:-----:|:----:|:---------------:|:---:|
-| 14.1374       | 0.31  | 10   | 15.7654         | 1.0 |
-| 13.2776       | 0.62  | 20   | 13.1005         | 1.0 |
-| 9.7262        | 0.94  | 30   | 6.3653          | 1.0 |
+| 3.7784        | 0.31  | 10   | 3.3180          | 1.0 |
+| 3.2502        | 0.62  | 20   | 3.0822          | 1.0 |
+| 3.0384        | 0.94  | 30   | 2.9854          | 1.0 |
 
 
 ### Framework versions