update model card README.md

README.md

@@ -21,7 +21,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 123.40425531914893
+      value: 186.6677311192719
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,8 +31,8 @@ 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 fleurs dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.8532
-- Wer: 123.4043
+- Loss: 1.0049
+- Wer: 186.6677
 
 ## Model description
 
@@ -52,21 +52,29 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 7.5e-06
-- train_batch_size: 4
-- eval_batch_size: 2
+- train_batch_size: 16
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_ratio: 0.5
-- training_steps: 2
+- lr_scheduler_warmup_ratio: 0.3
+- training_steps: 448
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer      |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.8019        | 0.5   | 1    | 1.8532          | 123.4043 |
-| 1.6763        | 1.0   | 2    | 1.8532          | 123.4043 |
+| 1.4112        | 0.1   | 44   | 1.4919          | 245.2978 |
+| 1.0501        | 0.2   | 88   | 1.2255          | 219.9425 |
+| 0.9033        | 0.29  | 132  | 1.1203          | 205.7800 |
+| 0.8142        | 1.06  | 176  | 1.0675          | 192.8788 |
+| 0.8029        | 1.16  | 220  | 1.0393          | 178.4289 |
+| 0.6324        | 1.25  | 264  | 1.0302          | 216.6055 |
+| 0.6971        | 2.02  | 308  | 1.0135          | 179.3709 |
+| 0.6051        | 2.12  | 352  | 1.0065          | 194.6352 |
+| 0.6048        | 2.21  | 396  | 1.0030          | 173.4792 |
+| 0.585         | 2.31  | 440  | 1.0049          | 186.6677 |
 
 
 ### Framework versions