update model card README.md

README.md

@@ -9,7 +9,7 @@ datasets:
 metrics:
 - wer
 model-index:
-- name: whisper tiny en-US - J3
+- name: whisper tiny en-US - J3v2
   results:
   - task:
       name: Automatic Speech Recognition
@@ -23,19 +23,19 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 0.3654073199527745
+      value: 0.33116883116883117
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# whisper tiny en-US - J3
+# whisper tiny en-US - J3v2
 
 This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14-en-US dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0413
-- Wer Ortho: 0.3603
-- Wer: 0.3654
+- Loss: 0.7183
+- Wer Ortho: 0.3381
+- Wer: 0.3312
 
 ## Model description
 
@@ -54,23 +54,20 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 32
-- eval_batch_size: 32
+- learning_rate: 1e-05
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: reduce_lr_on_plateau
-- lr_scheduler_warmup_steps: 100
-- training_steps: 2000
+- lr_scheduler_type: constant_with_warmup
+- lr_scheduler_warmup_steps: 50
+- training_steps: 500
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Wer Ortho | Wer    |
-|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|
-| 0.0001        | 35.71  | 500  | 0.8505          | 0.3430    | 0.3459 |
-| 0.0           | 71.43  | 1000 | 0.9093          | 0.3455    | 0.3501 |
-| 0.0           | 107.14 | 1500 | 0.9707          | 0.3553    | 0.3589 |
-| 0.0           | 142.86 | 2000 | 1.0413          | 0.3603    | 0.3654 |
+| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer    |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
+| 0.0012        | 17.86 | 500  | 0.7183          | 0.3381    | 0.3312 |
 
 
 ### Framework versions