update model card README.md

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 35.83106267029973
+      value: 0.3569482288828338
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,7 +33,7 @@ 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 PolyAI/minds14 dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.4068
-- Wer: 35.8311
+- Wer: 0.3569
 
 ## Model description
 
@@ -63,11 +63,11 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Wer     |
-|:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 0.6097        | 0.35  | 20   | 0.4507          | 35.5586 |
-| 0.4123        | 0.7   | 40   | 0.4169          | 35.0136 |
-| 0.3162        | 1.05  | 60   | 0.4068          | 35.8311 |
+| Training Loss | Epoch | Step | Validation Loss | Wer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 0.61          | 0.35  | 20   | 0.4505          | 0.3556 |
+| 0.4124        | 0.7   | 40   | 0.4167          | 0.3542 |
+| 0.3163        | 1.05  | 60   | 0.4068          | 0.3569 |
 
 
 ### Framework versions