Downloads · 30 days
8
8% of all-time downloads
dianavdavidson/wh_small_iv_30_70_indic_voices_52505__val_finetune_trial
wh_small_iv_30_70_indic_voices_52505__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
8
8% of all-time downloads
All-time downloads
102
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 |
|---|---|---|---|---|
| 1.6435 | 0.0158 | 50 | 1.2315 | 85.5241 |
| 0.9533 | 0.0317 | 100 | 0.9746 | 66.8702 |
| 0.8989 | 0.0475 | 150 | 0.8648 | 62.4506 |
| 0.8826 | 0.0633 | 200 | 0.7588 | 60.7987 |
| 0.7247 | 0.0792 | 250 | 0.6702 | 62.4462 |
| 0.6214 | 0.0950 | 300 | 0.5726 | 54.9996 |
| 0.4723 | 0.1108 | 350 | 0.4893 | 53.6069 |
| 0.4424 | 0.1267 | 400 | 0.4545 | 50.6854 |
| 0.4292 | 0.1425 | 450 | 0.4438 | 49.7672 |
| 0.4408 | 0.1583 | 500 | 0.4306 | 48.3218 |