navin-kumar-j
/

whisper-base-en-w-pcd-10-2

Automatic Speech Recognition

Generated from Trainer

Model card Files Files and versions

Metrics Training metrics Community

navin-kumar-j commited on May 15, 2025

Commit

8cdcc2b

·

verified ·

1 Parent(s): d8816d7

End of training

Files changed (1) hide show

README.md +6 -6

README.md CHANGED Viewed

@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [openai/whisper-base.en](https://huggingface.co/openai/whisper-base.en) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0804
 - Wer: 0.7863
 ## Model description
@@ -54,11 +54,11 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss | Wer    |
 |:-------------:|:------:|:----:|:---------------:|:------:|
-| 26.7036       | 0.9091 | 40   | 27.8273         | 1.0    |
-| 8.3609        | 1.8182 | 80   | 5.3806          | 1.0    |
-| 1.976         | 2.7273 | 120  | 1.8119          | 0.9160 |
-| 1.3051        | 3.6364 | 160  | 1.3559          | 0.7634 |
-| 1.0115        | 4.5455 | 200  | 1.0804          | 0.7863 |
 ### Framework versions

 This model is a fine-tuned version of [openai/whisper-base.en](https://huggingface.co/openai/whisper-base.en) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 1.3819
 - Wer: 0.7863
 ## Model description
 | Training Loss | Epoch  | Step | Validation Loss | Wer    |
 |:-------------:|:------:|:----:|:---------------:|:------:|
+| 36.1644       | 0.9091 | 40   | 24.3079         | 1.0    |
+| 5.8058        | 1.8182 | 80   | 5.1572          | 0.8473 |
+| 2.9137        | 2.7273 | 120  | 2.4350          | 0.8779 |
+| 1.8303        | 3.6364 | 160  | 1.6639          | 0.8702 |
+| 1.3301        | 4.5455 | 200  | 1.3819          | 0.7863 |
 ### Framework versions