update model card README.md

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 32.142857142857146
+      value: 78.57142857142857
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ 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 test_data dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0002
-- Wer: 32.1429
+- Loss: 0.5435
+- Wer: 78.5714
 
 ## Model description
 
@@ -66,10 +66,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
-| No log        | 10.0  | 10   | 0.4450          | 0.0     |
-| No log        | 20.0  | 20   | 0.3230          | 0.0     |
-| 0.5769        | 30.0  | 30   | 0.0041          | 0.0     |
-| 0.5769        | 40.0  | 40   | 0.0002          | 32.1429 |
+| No log        | 10.0  | 10   | 2.2425          | 7.1429  |
+| No log        | 20.0  | 20   | 0.6651          | 0.0     |
+| 2.4375        | 30.0  | 30   | 0.5776          | 35.7143 |
+| 2.4375        | 40.0  | 40   | 0.5435          | 78.5714 |
 
 
 ### Framework versions