End of training

README.md

@@ -25,7 +25,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 0.49260820121747273
+      value: 0.4430396682052311
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -35,8 +35,8 @@ 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 17.0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0942
-- Wer: 0.4926
+- Loss: 0.0858
+- Wer: 0.4430
 
 ## Model description
 
@@ -66,18 +66,22 @@ The following hyperparameters were used during training:
 - total_eval_batch_size: 4
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 500
-- training_steps: 4000
+- lr_scheduler_warmup_steps: 1000
+- training_steps: 8000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss | Wer    |
 |:-------------:|:------:|:----:|:---------------:|:------:|
-| 0.2215        | 0.2175 | 1000 | 0.1887          | 0.6911 |
-| 0.1717        | 0.4349 | 2000 | 0.1333          | 0.5892 |
-| 0.1397        | 0.6524 | 3000 | 0.1067          | 0.5247 |
-| 0.1275        | 0.8698 | 4000 | 0.0942          | 0.4926 |
+| 0.2913        | 0.2175 | 1000 | 0.2658          | 0.7758 |
+| 0.2112        | 0.4349 | 2000 | 0.1918          | 0.6780 |
+| 0.1733        | 0.6524 | 3000 | 0.1544          | 0.6206 |
+| 0.1485        | 0.8698 | 4000 | 0.1279          | 0.5651 |
+| 0.1029        | 1.0873 | 5000 | 0.1102          | 0.5119 |
+| 0.0989        | 1.3047 | 6000 | 0.0983          | 0.4775 |
+| 0.0935        | 1.5222 | 7000 | 0.0901          | 0.4566 |
+| 0.0863        | 1.7396 | 8000 | 0.0858          | 0.4430 |
 
 
 ### Framework versions