update model card README.md

README.md

@@ -7,9 +7,24 @@ tags:
 - generated_from_trainer
 datasets:
 - mozilla-foundation/common_voice_11_0
+metrics:
+- wer
 model-index:
 - name: Whisper Small Japanese - Kimbo Chen
-  results: []
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Common Voice 11.0
+      type: mozilla-foundation/common_voice_11_0
+      config: ja
+      split: test
+      args: ja
+    metrics:
+    - name: Wer
+      type: wer
+      value: 88.31039863810469
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -19,13 +34,8 @@ 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 11.0 dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.5878
-- eval_wer: 88.3104
-- eval_runtime: 1623.9093
-- eval_samples_per_second: 2.835
-- eval_steps_per_second: 0.355
-- epoch: 39.0
-- step: 4000
+- Loss: 0.5878
+- Wer: 88.3104
 
 ## Model description
 
@@ -50,10 +60,19 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 500
-- training_steps: 5000
+- training_steps: 1000
 - mixed_precision_training: Native AMP
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer     |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|
+| 0.0066        | 9.02  | 1000 | 0.4680          | 90.5377 |
+| 0.003         | 19.01 | 2000 | 0.5128          | 89.3602 |
+| 0.0006        | 29.01 | 3000 | 0.5657          | 88.7218 |
+| 0.0003        | 39.0  | 4000 | 0.5878          | 88.3104 |
+
+
 ### Framework versions
 
 - Transformers 4.26.0.dev0