Downloads · 30 days
5
5% of all-time downloads
dianavdavidson/wh_small_iv_30_70_flattened_indic_voices_52545__val_finetune_trial
wh_small_iv_30_70_flattened_indic_voices_52545__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
5
5% of all-time downloads
All-time downloads
99
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 | 85.5285 |
| 0.9533 | 0.0317 | 100 | 0.9746 | 66.8702 |
| 0.8990 | 0.0475 | 150 | 0.8648 | 62.5912 |
| 0.8825 | 0.0633 | 200 | 0.7588 | 61.2292 |
| 0.7250 | 0.0792 | 250 | 0.6703 | 62.5560 |
| 0.6214 | 0.0950 | 300 | 0.5727 | 54.9381 |
| 0.4723 | 0.1108 | 350 | 0.4894 | 53.6289 |
| 0.4425 | 0.1267 | 400 | 0.4545 | 50.5404 |
| 0.4293 | 0.1425 | 450 | 0.4438 | 50.1098 |
| 0.4411 | 0.1583 | 500 | 0.4306 | 48.3789 |