End of training

README.md

@@ -24,7 +24,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 57.14285714285714
+      value: 58.44155844155844
 ---
 
 <!-- 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 11.0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9139
-- Wer: 57.1429
+- Loss: 0.9705
+- Wer: 58.4416
 
 ## Model description
 
@@ -67,16 +67,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 0.0112        | 20.0  | 1000 | 0.7359          | 61.0390 |
-| 0.0           | 40.0  | 2000 | 0.8434          | 57.1429 |
-| 0.0           | 60.0  | 3000 | 0.8839          | 57.1429 |
-| 0.0           | 80.0  | 4000 | 0.9055          | 57.1429 |
-| 0.0           | 100.0 | 5000 | 0.9139          | 57.1429 |
+| 0.0021        | 20.0  | 1000 | 0.8610          | 61.0390 |
+| 0.0           | 40.0  | 2000 | 0.9097          | 59.7403 |
+| 0.0           | 60.0  | 3000 | 0.9417          | 59.7403 |
+| 0.0           | 80.0  | 4000 | 0.9622          | 59.7403 |
+| 0.0           | 100.0 | 5000 | 0.9705          | 58.4416 |
 
 
 ### Framework versions
 
 - Transformers 4.41.0
-- Pytorch 2.2.1+cu121
+- Pytorch 2.3.0+cu121
 - Datasets 2.19.1
 - Tokenizers 0.19.1