SamagraDataGov
/

whisper-tiny-hindi2_test

Automatic Speech Recognition

Generated from Trainer

Model card Files Files and versions

Metrics Training metrics Community

SamagraDataGov commited on Jun 29, 2024

Commit

9e7a0f0

·

verified ·

1 Parent(s): b95e872

Model save

Files changed (1) hide show

README.md +7 -7

README.md CHANGED Viewed

@@ -17,8 +17,8 @@ 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: 0.3585
-- Wer: 38.2799
 ## Model description
@@ -53,11 +53,11 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss | Wer     |
 |:-------------:|:------:|:----:|:---------------:|:-------:|
-| 0.312         | 1.2698 | 40   | 0.2682          | 38.6172 |
-| 0.1574        | 2.5397 | 80   | 0.2760          | 37.6054 |
-| 0.0914        | 3.8095 | 120  | 0.2983          | 37.6054 |
-| 0.0579        | 5.0794 | 160  | 0.3087          | 37.7740 |
-| 0.028         | 6.3492 | 200  | 0.3585          | 38.2799 |
 ### Framework versions

 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: 0.2674
+- Wer: 32.3777
 ## Model description
 | Training Loss | Epoch  | Step | Validation Loss | Wer     |
 |:-------------:|:------:|:----:|:---------------:|:-------:|
+| 0.2955        | 1.2698 | 40   | 0.2317          | 36.0034 |
+| 0.1522        | 2.5397 | 80   | 0.2200          | 34.4013 |
+| 0.0819        | 3.8095 | 120  | 0.2255          | 32.5464 |
+| 0.0463        | 5.0794 | 160  | 0.2483          | 32.7993 |
+| 0.0289        | 6.3492 | 200  | 0.2674          | 32.3777 |
 ### Framework versions