End of training

README.md

@@ -14,16 +14,16 @@ model-index:
 - name: Whisper Small Bashkir
   results:
   - task:
-      type: automatic-speech-recognition
       name: Automatic Speech Recognition
+      type: automatic-speech-recognition
     dataset:
       name: Common Voice 17.0 (ba)
       type: stdbug/common-voice-17-ba
       args: 'config: ba, split: test'
     metrics:
-    - type: wer
-      value: 35.52960800667223
-      name: Wer
+    - name: Wer
+      type: wer
+      value: 26.41273722821753
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,8 +33,8 @@ 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 (ba) dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3040
-- Wer: 35.5296
+- Loss: 0.1734
+- Wer: 26.4127
 
 ## Model description
 
@@ -60,14 +60,14 @@ The following hyperparameters were used during training:
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- training_steps: 3341
+- training_steps: 13842
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Wer     |
-|:-------------:|:------:|:----:|:---------------:|:-------:|
-| 0.2326        | 0.9997 | 3341 | 0.3040          | 35.5296 |
+| Training Loss | Epoch  | Step  | Validation Loss | Wer     |
+|:-------------:|:------:|:-----:|:---------------:|:-------:|
+| 0.1263        | 0.9999 | 13842 | 0.1734          | 26.4127 |
 
 
 ### Framework versions