Update with WER score
Browse files
README.md
CHANGED
|
@@ -19,8 +19,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 19 |
|
| 20 |
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the openai/whisper-tiny dataset.
|
| 21 |
It achieves the following results on the evaluation set:
|
|
|
|
| 22 |
- eval_loss: 4.6150
|
| 23 |
- eval_runtime: 94.5398
|
|
|
|
| 24 |
- eval_samples_per_second: 0.529
|
| 25 |
- eval_steps_per_second: 0.529
|
| 26 |
- step: 0
|
|
|
|
| 19 |
|
| 20 |
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the openai/whisper-tiny dataset.
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
+
WER: 0.931
|
| 23 |
- eval_loss: 4.6150
|
| 24 |
- eval_runtime: 94.5398
|
| 25 |
+
- eval_wer: 0.9308
|
| 26 |
- eval_samples_per_second: 0.529
|
| 27 |
- eval_steps_per_second: 0.529
|
| 28 |
- step: 0
|