End of training

README.md

@@ -24,7 +24,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 16.0285941223193
+      value: 15.822081016679904
 ---
 
 <!-- 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: 0.3760
-- Wer: 16.0286
+- Loss: 0.3497
+- Wer: 15.8221
 
 ## Model description
 
@@ -61,7 +61,7 @@ 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: 1600
+- training_steps: 800
 
 ### Training results
 
@@ -69,12 +69,8 @@ The following hyperparameters were used during training:
 |:-------------:|:------:|:----:|:---------------:|:-------:|
 | 0.2956        | 0.6667 | 200  | 0.4193          | 20.5242 |
 | 0.1807        | 1.3333 | 400  | 0.3708          | 16.9341 |
-| 0.2229        | 2.0    | 600  | 0.3558          | 17.0612 |
-| 0.0734        | 2.6667 | 800  | 0.3546          | 15.1708 |
-| 0.0218        | 3.3333 | 1000 | 0.3663          | 15.3614 |
-| 0.0294        | 4.0    | 1200 | 0.3634          | 16.0604 |
-| 0.0036        | 4.6667 | 1400 | 0.3714          | 15.3932 |
-| 0.0018        | 5.3333 | 1600 | 0.3760          | 16.0286 |
+| 0.2201        | 2.0    | 600  | 0.3528          | 16.8070 |
+| 0.0694        | 2.6667 | 800  | 0.3497          | 15.8221 |
 
 
 ### Framework versions