DewiBrynJones
/

whisper-tiny-ft-ccv-en-cy

Automatic Speech Recognition

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

DewiBrynJones commited on Mar 20

Commit

2aed67c

•

1 Parent(s): b097ef3

Model save

Files changed (1) hide show

README.md +6 -6

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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5462
-- Wer: 35.3640
 ## Model description
@@ -52,10 +52,10 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 0.7059        | 0.25  | 1000 | 0.7390          | 44.4910 |
-| 0.5534        | 0.5   | 2000 | 0.6116          | 39.2168 |
-| 0.5087        | 0.75  | 3000 | 0.5615          | 36.0193 |
-| 0.4749        | 1.01  | 4000 | 0.5462          | 35.3640 |
 ### Framework versions

 This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.5477
+- Wer: 34.3428
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
+| 0.7097        | 0.25  | 1000 | 0.7389          | 43.5556 |
+| 0.5583        | 0.5   | 2000 | 0.6130          | 38.2386 |
+| 0.5141        | 0.75  | 3000 | 0.5637          | 35.1617 |
+| 0.4805        | 1.01  | 4000 | 0.5477          | 34.3428 |
 ### Framework versions