Downloads · 30 days
7
7% of all-time downloads
dianavdavidson/wh_l_v3_iv_30_70_indic_voices_52508__val_finetune_trial
wh_l_v3_iv_30_70_indic_voices_52508__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
7
7% of all-time downloads
All-time downloads
107
Public
Parameters
1.5B
30.9 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors6.2 GB · 100%
From the Hugging Face model README
This model is a fine-tuned version of openai/whisper-large-v3 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 |
|---|---|---|---|---|
| 0.6992 | 0.0158 | 50 | 0.5604 | 37.7954 |
| 0.3589 | 0.0317 | 100 | 0.3378 | 36.8289 |
| 0.3320 | 0.0475 | 150 | 0.2995 | 37.8657 |
| 0.3566 | 0.0633 | 200 | 0.2780 | 67.3798 |
| 0.2967 | 0.0792 | 250 | 0.2751 | 42.9004 |
| 0.2719 | 0.0950 | 300 | 0.2573 | 97.9220 |
| 0.2528 | 0.1108 | 350 | 0.2617 | 79.2198 |
| 0.2488 | 0.1267 | 400 | 0.2501 | 116.2244 |
| 0.2372 | 0.1425 | 450 | 0.2452 | 131.2231 |
| 0.2545 | 0.1583 | 500 | 0.2492 | 75.1252 |