End of training

README.md

@@ -17,8 +17,8 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0282
-- Wer: 29.4626
+- Loss: 0.0214
+- Wer: 24.8202
 
 ## Model description
 
@@ -37,8 +37,8 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2.67e-05
-- train_batch_size: 32
+- learning_rate: 2e-05
+- train_batch_size: 24
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
@@ -51,8 +51,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Wer     |
 |:-------------:|:------:|:----:|:---------------:|:-------:|
-| 0.0386        | 0.4902 | 500  | 0.0354          | 33.5893 |
-| 0.0319        | 0.9804 | 1000 | 0.0282          | 29.4626 |
+| 0.025         | 0.3676 | 500  | 0.0263          | 28.7131 |
+| 0.0224        | 0.7353 | 1000 | 0.0214          | 24.8202 |
 
 
 ### Framework versions