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 [scasutt/Prototype_training](https://huggingface.co/scasutt/Prototype_training) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5002
-- Wer: 0.5111
+- Loss: 0.3433
+- Wer: 0.4532
 
 ## Model description
 
@@ -49,8 +49,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 6.7314        | 1.47  | 100  | 2.9310          | 0.9983 |
-| 1.8053        | 2.94  | 200  | 0.5002          | 0.5111 |
+| 0.7444        | 1.47  | 100  | 0.3494          | 0.4556 |
+| 0.5918        | 2.94  | 200  | 0.3433          | 0.4532 |
 
 
 ### Framework versions