End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 68.57318573185732
+      value: 0.4040590405904059
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,9 +32,9 @@ 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: 0.7143
-- Wer Ortho: 68.5972
-- Wer: 68.5732
+- Loss: 0.7329
+- Wer Ortho: 41.4414
+- Wer: 0.4041
 
 ## Model description
 
@@ -55,18 +55,18 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
 - train_batch_size: 16
-- eval_batch_size: 16
+- eval_batch_size: 64
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant_with_warmup
-- lr_scheduler_warmup_steps: 50
+- lr_scheduler_warmup_steps: 500
 - training_steps: 500
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer     |
-|:-------------:|:-----:|:----:|:---------------:|:---------:|:-------:|
-| 0.002         | 17.24 | 500  | 0.7143          | 68.5972   | 68.5732 |
+| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer    |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
+| 0.004         | 17.24 | 500  | 0.7329          | 41.4414   | 0.4041 |
 
 
 ### Framework versions