End of training

README.md

@@ -9,9 +9,22 @@ tags:
 - generated_from_trainer
 datasets:
 - Chinese_english
+metrics:
+- wer
 model-index:
 - name: Whisper tiny Chinese
-  results: []
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Chinese English
+      type: Chinese_english
+      args: 'config: default, split: test'
+    metrics:
+    - name: Wer
+      type: wer
+      value: 15.933280381254963
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -20,6 +33,9 @@ should probably proofread and complete it, then remove this comment. -->
 # Whisper tiny Chinese
 
 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: 0.3506
+- Wer: 15.9333
 
 ## Model description
 
@@ -45,7 +61,16 @@ 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: 1400
+- training_steps: 600
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Wer     |
+|:-------------:|:------:|:----:|:---------------:|:-------:|
+| 0.3967        | 0.6667 | 200  | 0.4181          | 20.5401 |
+| 0.2614        | 1.3333 | 400  | 0.3771          | 18.1255 |
+| 0.222         | 2.0    | 600  | 0.3506          | 15.9333 |
+
 
 ### Framework versions