kawther1
/

whisper-LARGE-AR2

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

kawther1 commited on May 29, 2024

Commit

4ca9b00

·

verified ·

1 Parent(s): 3f03590

END

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -20,9 +20,9 @@ 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 the common_voice_16_1 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.7675
-- Wer Ortho: 45.1883
-- Wer: 47.2366
 ## Model description
@@ -56,7 +56,7 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:-------:|
-| 1.0629        | 0.16  | 10   | 1.7675          | 45.1883   | 47.2366 |
 ### Framework versions

 This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the common_voice_16_1 dataset.
 It achieves the following results on the evaluation set:
+- Loss: 1.1097
+- Wer Ortho: 47.2803
+- Wer: 50.2591
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:-------:|
+| 0.5456        | 0.16  | 10   | 1.1097          | 47.2803   | 50.2591 |
 ### Framework versions