techiaith
/

whisper-large-v3-ft-btb-cv-cy

Automatic Speech Recognition

Generated from Trainer

Model card Files Files and versions Metrics Training metrics

DewiBrynJones commited on Oct 4, 2024

Commit

44e9e13

·

verified ·

1 Parent(s): 5ddd1fc

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-large-v3](https://huggingface.co/openai/whisper-large-v3) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3840
-- Wer: 0.2795
 ## Model description
@@ -53,11 +53,11 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss | Wer    |
 |:-------------:|:------:|:----:|:---------------:|:------:|
-| 0.404         | 0.5711 | 1000 | 0.4849          | 0.3564 |
-| 0.2489        | 1.1422 | 2000 | 0.4184          | 0.3156 |
-| 0.2528        | 1.7133 | 3000 | 0.3892          | 0.2921 |
-| 0.1567        | 2.2844 | 4000 | 0.3910          | 0.2868 |
-| 0.1303        | 2.8555 | 5000 | 0.3840          | 0.2795 |
 ### Framework versions

 This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.3838
+- Wer: 0.2732
 ## Model description
 | Training Loss | Epoch  | Step | Validation Loss | Wer    |
 |:-------------:|:------:|:----:|:---------------:|:------:|
+| 0.4047        | 0.5711 | 1000 | 0.4849          | 0.3505 |
+| 0.2476        | 1.1422 | 2000 | 0.4187          | 0.3137 |
+| 0.2527        | 1.7133 | 3000 | 0.3882          | 0.2901 |
+| 0.1568        | 2.2844 | 4000 | 0.3902          | 0.2816 |
+| 0.1313        | 2.8555 | 5000 | 0.3838          | 0.2732 |
 ### Framework versions