Downloads · 30 days
3
3% of all-time downloads
dianavdavidson/wh_small_mucs_30_70_flattened_mucs_52549__val_finetune_trial
wh_small_mucs_30_70_flattened_mucs_52549__val_finetune_trial is a automatic speech recognition model from dianavdavidson. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
3
3% of all-time downloads
All-time downloads
96
Public
Parameters
242M
4.8 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors967 MB · 100%
From the Hugging Face model README
This model is a fine-tuned version of openai/whisper-small on an unknown dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Global Wer |
|---|---|---|---|---|
| 1.5540 | 0.0133 | 50 | 1.1463 | 50.1939 |
| 1.0086 | 0.0266 | 100 | 0.8635 | 47.7084 |
| 0.9138 | 0.0399 | 150 | 0.7298 | 37.3088 |
| 0.7471 | 0.0531 | 200 | 0.6393 | 48.3183 |
| 0.5346 | 0.0664 | 250 | 0.5559 | 35.8036 |
| 0.5334 | 0.0797 | 300 | 0.4780 | 35.3549 |
| 0.4308 | 0.0930 | 350 | 0.4062 | 34.7471 |
| 0.4109 | 0.1063 | 400 | 0.3811 | 35.8864 |
| 0.3786 | 0.1196 | 450 | 0.3628 | 31.3706 |
| 0.3947 | 0.1329 | 500 | 0.3480 | 30.5799 |