Reformat eval metrics
Browse filesReformat eval metrics to be parsed by course certification script.
README.md
CHANGED
|
@@ -16,6 +16,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
- eval_loss: 0.6170
|
| 20 |
- eval_wer_ortho: 0.3880
|
| 21 |
- eval_wer: 0.3512
|
|
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
|
| 20 |
+
- Loss: 0.6170
|
| 21 |
+
- Wer Ortho: 0.3880
|
| 22 |
+
- Wer: 0.3512
|
| 23 |
+
|
| 24 |
- eval_loss: 0.6170
|
| 25 |
- eval_wer_ortho: 0.3880
|
| 26 |
- eval_wer: 0.3512
|