update model card README.md

README.md

@@ -24,7 +24,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 59.524168046980876
+      value: 36.289715404306584
 ---
 
 <!-- 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 Zeroth-Korean dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.6946
-- Wer: 59.5242
+- Loss: 0.3234
+- Wer: 36.2897
 
 ## Model description
 
@@ -60,15 +60,17 @@ 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: 1
-- training_steps: 1
+- lr_scheduler_warmup_steps: 500
+- training_steps: 3000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 2.6768        | 0.0   | 1    | 2.6946          | 59.5242 |
+| 0.6968        | 0.72  | 1000 | 0.4325          | 42.5237 |
+| 0.2949        | 1.44  | 2000 | 0.3495          | 38.9098 |
+| 0.2274        | 2.16  | 3000 | 0.3234          | 36.2897 |
 
 
 ### Framework versions