End of training

README.md

@@ -24,7 +24,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 30.81815492541098
+      value: 30.788572877488065
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -34,8 +34,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Mix data dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3450
-- Wer: 30.8182
+- Loss: 0.3451
+- Wer: 30.7886
 
 ## Model description
 
@@ -70,14 +70,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Wer     |
 |:-------------:|:------:|:----:|:---------------:|:-------:|
-| 0.1442        | 0.1129 | 500  | 0.3683          | 32.9502 |
-| 0.1532        | 0.2258 | 1000 | 0.3707          | 32.7589 |
-| 0.1478        | 0.3388 | 1500 | 0.3663          | 33.0019 |
-| 0.1375        | 0.4517 | 2000 | 0.3625          | 31.7817 |
-| 0.1509        | 0.5646 | 2500 | 0.3552          | 32.2106 |
-| 0.139         | 0.6775 | 3000 | 0.3510          | 31.5271 |
-| 0.1404        | 0.7904 | 3500 | 0.3473          | 30.9787 |
-| 0.1349        | 0.9033 | 4000 | 0.3450          | 30.8182 |
+| 0.1438        | 0.1129 | 500  | 0.3669          | 32.7896 |
+| 0.154         | 0.2258 | 1000 | 0.3710          | 32.7262 |
+| 0.1482        | 0.3388 | 1500 | 0.3663          | 33.0875 |
+| 0.1383        | 0.4517 | 2000 | 0.3626          | 32.0173 |
+| 0.1513        | 0.5646 | 2500 | 0.3559          | 32.4166 |
+| 0.1387        | 0.6775 | 3000 | 0.3514          | 30.9249 |
+| 0.1407        | 0.7904 | 3500 | 0.3479          | 30.8963 |
+| 0.1353        | 0.9033 | 4000 | 0.3451          | 30.7886 |
 
 
 ### Framework versions