End of training

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0427
-- Wer: 18.2384
+- Loss: 0.0424
+- Wer: 18.1637
 
 ## Model description
 
@@ -53,12 +53,12 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 0.0483        | 0.79  | 1000 | 0.0804          | 40.4578 |
-| 0.0238        | 1.58  | 2000 | 0.0514          | 27.3700 |
-| 0.0106        | 2.37  | 3000 | 0.0449          | 22.5678 |
-| 0.0041        | 3.16  | 4000 | 0.0396          | 18.8604 |
-| 0.0038        | 3.95  | 5000 | 0.0406          | 19.6317 |
-| 0.0016        | 4.74  | 6000 | 0.0427          | 18.2384 |
+| 0.0482        | 0.79  | 1000 | 0.0801          | 40.4827 |
+| 0.0238        | 1.58  | 2000 | 0.0514          | 27.4944 |
+| 0.0105        | 2.37  | 3000 | 0.0447          | 22.8415 |
+| 0.0044        | 3.16  | 4000 | 0.0403          | 19.3580 |
+| 0.0037        | 3.95  | 5000 | 0.0408          | 19.3083 |
+| 0.0016        | 4.74  | 6000 | 0.0424          | 18.1637 |
 
 
 ### Framework versions