Commit ·
7f88851
1
Parent(s): 2b36ece
Training in progress, step 3500
Browse files
README.md
CHANGED
|
@@ -18,14 +18,14 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the arrow dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
- eval_loss: 0.
|
| 22 |
-
- eval_wer_ortho:
|
| 23 |
-
- eval_wer: 2.
|
| 24 |
-
- eval_runtime:
|
| 25 |
-
- eval_samples_per_second: 3.
|
| 26 |
-
- eval_steps_per_second: 0.
|
| 27 |
-
- epoch: 0.
|
| 28 |
-
- step:
|
| 29 |
|
| 30 |
## Model description
|
| 31 |
|
|
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the arrow dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- eval_loss: 0.0287
|
| 22 |
+
- eval_wer_ortho: 16.5967
|
| 23 |
+
- eval_wer: 2.4205
|
| 24 |
+
- eval_runtime: 11555.3152
|
| 25 |
+
- eval_samples_per_second: 3.797
|
| 26 |
+
- eval_steps_per_second: 0.079
|
| 27 |
+
- epoch: 0.5748
|
| 28 |
+
- step: 3500
|
| 29 |
|
| 30 |
## Model description
|
| 31 |
|