End of training

README.md

@@ -24,7 +24,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 9.512195121951219
+      value: 13.963463065925339
 ---
 
 <!-- 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: 0.2023
-- Wer: 9.5122
+- Loss: 0.3168
+- Wer: 13.9635
 
 ## Model description
 
@@ -61,21 +61,20 @@ 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: 2000
+- training_steps: 1500
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss | Wer     |
 |:-------------:|:------:|:----:|:---------------:|:-------:|
-| 0.3187        | 0.5086 | 500  | 0.2582          | 12.7073 |
-| 0.1756        | 1.0173 | 1000 | 0.2165          | 9.8780  |
-| 0.0827        | 1.5259 | 1500 | 0.2084          | 9.6585  |
-| 0.0741        | 2.0346 | 2000 | 0.2023          | 9.5122  |
+| 0.3628        | 0.8333 | 500  | 0.3393          | 15.7903 |
+| 0.1092        | 1.6667 | 1000 | 0.3252          | 14.8689 |
+| 0.0513        | 2.5    | 1500 | 0.3168          | 13.9635 |
 
 
 ### Framework versions
 
 - Transformers 4.49.0
 - Pytorch 2.6.0+cu124
-- Datasets 3.4.0
+- Datasets 3.5.0
 - Tokenizers 0.21.1