update model card README.md

README.md

@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [crossdelenna/whisper-base.en](https://huggingface.co/crossdelenna/whisper-base.en) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0265
-- Wer: 1.7660
+- Loss: 0.0018
+- Wer: 0.7385
 
 ## Model description
 
@@ -48,12 +48,12 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Wer     |
-|:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 0.5324        | 2.0   | 500  | 0.3535          | 11.4524 |
-| 0.2141        | 4.0   | 1000 | 0.1069          | 5.9510  |
-| 0.0816        | 6.0   | 1500 | 0.0403          | 2.2691  |
-| 0.0436        | 8.0   | 2000 | 0.0265          | 1.7660  |
+| Training Loss | Epoch | Step | Validation Loss | Wer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 0.0254        | 2.0   | 500  | 0.0133          | 1.6269 |
+| 0.0119        | 4.0   | 1000 | 0.0049          | 0.9740 |
+| 0.0051        | 6.0   | 1500 | 0.0021          | 0.7064 |
+| 0.0026        | 8.0   | 2000 | 0.0018          | 0.7385 |
 
 
 ### Framework versions