End of training

README.md

@@ -24,7 +24,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 40.43020749693614
+      value: 40.49254109791658
 ---
 
 <!-- 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 Common Voice 15.0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3828
-- Wer: 40.4302
+- Loss: 0.3827
+- Wer: 40.4925
 
 ## Model description
 
@@ -70,14 +70,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Wer     |
 |:-------------:|:------:|:----:|:---------------:|:-------:|
-| 0.6715        | 0.1129 | 500  | 0.7162          | 66.9030 |
-| 0.4722        | 0.2258 | 1000 | 0.5434          | 54.6750 |
-| 0.4207        | 0.3388 | 1500 | 0.4768          | 49.2076 |
-| 0.3884        | 0.4517 | 2000 | 0.4404          | 45.1739 |
-| 0.3734        | 0.5646 | 2500 | 0.4167          | 43.9420 |
-| 0.3389        | 0.6775 | 3000 | 0.3994          | 41.2205 |
-| 0.3405        | 0.7904 | 3500 | 0.3887          | 41.2110 |
-| 0.3087        | 0.9033 | 4000 | 0.3828          | 40.4302 |
+| 0.6714        | 0.1129 | 500  | 0.7163          | 66.8396 |
+| 0.4722        | 0.2258 | 1000 | 0.5435          | 54.3887 |
+| 0.4207        | 0.3388 | 1500 | 0.4766          | 49.0312 |
+| 0.3891        | 0.4517 | 2000 | 0.4403          | 45.2288 |
+| 0.3737        | 0.5646 | 2500 | 0.4167          | 44.0403 |
+| 0.3386        | 0.6775 | 3000 | 0.3994          | 41.2405 |
+| 0.3402        | 0.7904 | 3500 | 0.3887          | 41.2300 |
+| 0.3089        | 0.9033 | 4000 | 0.3827          | 40.4925 |
 
 
 ### Framework versions