End of training

README.md

@@ -20,8 +20,8 @@ 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 idiotDeveloper/vts_sample_data_1.0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5241
-- Cer: 138.6364
+- Loss: 0.0365
+- Cer: 0.0
 
 ## Model description
 
@@ -47,17 +47,15 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 20
-- training_steps: 200
+- training_steps: 50
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Cer      |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.206         | 50.0  | 50   | 0.3984          | 100.0    |
-| 0.0064        | 100.0 | 100  | 0.4459          | 100.0    |
-| 0.0           | 150.0 | 150  | 0.5048          | 87.5     |
-| 0.0           | 200.0 | 200  | 0.5241          | 138.6364 |
+| Training Loss | Epoch | Step | Validation Loss | Cer   |
+|:-------------:|:-----:|:----:|:---------------:|:-----:|
+| 0.0588        | 25.0  | 25   | 0.0556          | 100.0 |
+| 0.0352        | 50.0  | 50   | 0.0365          | 0.0   |
 
 
 ### Framework versions