End of training

README.md

@@ -24,7 +24,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 17.776012708498808
+      value: 16.25099285146942
 ---
 
 <!-- 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-tiny](https://huggingface.co/openai/whisper-tiny) on the Chinese English dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3647
-- Wer: 17.7760
+- Loss: 0.3512
+- Wer: 16.2510
 
 ## Model description
 
@@ -61,15 +61,14 @@ 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: 1500
+- training_steps: 1000
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss | Wer     |
 |:-------------:|:------:|:----:|:---------------:|:-------:|
-| 0.2232        | 1.6667 | 500  | 0.3613          | 16.8229 |
-| 0.0095        | 3.3333 | 1000 | 0.3598          | 16.4575 |
-| 0.0032        | 5.0    | 1500 | 0.3647          | 17.7760 |
+| 0.2231        | 1.6667 | 500  | 0.3612          | 16.9976 |
+| 0.0141        | 3.3333 | 1000 | 0.3512          | 16.2510 |
 
 
 ### Framework versions