End of training

README.md

@@ -18,8 +18,8 @@ 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 None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1016
-- Wer: 46.9010
+- Loss: 0.1823
+- Wer: 8.7755
 
 ## Model description
 
@@ -45,26 +45,24 @@ 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: 500
-- training_steps: 2000
+- training_steps: 3000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch   | Step | Validation Loss | Wer     |
 |:-------------:|:-------:|:----:|:---------------:|:-------:|
-| 0.3644        | 4.1667  | 250  | 0.7955          | 59.0359 |
-| 0.1196        | 8.3333  | 500  | 0.8738          | 54.2745 |
-| 0.0458        | 12.5    | 750  | 0.9793          | 51.6742 |
-| 0.0239        | 16.6667 | 1000 | 1.0239          | 51.2942 |
-| 0.0118        | 20.8333 | 1250 | 1.0658          | 48.8601 |
-| 0.0021        | 25.0    | 1500 | 1.0849          | 47.7321 |
-| 0.0004        | 29.1667 | 1750 | 1.0976          | 47.6253 |
-| 0.0004        | 33.3333 | 2000 | 1.1016          | 46.9010 |
+| 0.1101        | 8.3333  | 500  | 0.9455          | 59.9493 |
+| 0.0295        | 16.6667 | 1000 | 1.0721          | 50.0664 |
+| 0.0117        | 25.0    | 1500 | 1.1477          | 50.5491 |
+| 0.0008        | 33.3333 | 2000 | 1.1674          | 47.4840 |
+| 0.0016        | 41.6667 | 2500 | 0.1804          | 9.2610  |
+| 0.0004        | 50.0    | 3000 | 0.1823          | 8.7755  |
 
 
 ### Framework versions
 
 - Transformers 4.44.2
 - Pytorch 2.4.0+cu121
-- Datasets 2.21.0
+- Datasets 3.0.0
 - Tokenizers 0.19.1