Downloads · 30 days
3
3% of all-time downloads
dianavdavidson/wh_l_v3_iv_no_lg_id_indic_voices_52031_trial
wh_l_v3_iv_no_lg_id_indic_voices_52031_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
94
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 |
|---|---|---|---|---|
| 0.8759 | 0.0110 | 50 | 0.8147 | 79.9391 |
| 0.3032 | 0.0220 | 100 | 0.3335 | 102.3362 |
| 0.3048 | 0.0330 | 150 | 0.3161 | 85.4749 |
| 0.2521 | 0.0440 | 200 | 0.2869 | 77.1458 |
| 0.2567 | 0.0550 | 250 | 0.2961 | 63.3316 |
| 0.2719 | 0.0660 | 300 | 0.2738 | 58.3037 |
| 0.2759 | 0.0770 | 350 | 0.2738 | 77.0442 |
| 0.2851 | 0.0880 | 400 | 0.2666 | 65.2108 |
| 0.2655 | 0.0990 | 450 | 0.2723 | 63.4840 |
| 0.2029 | 0.1100 | 500 | 0.2602 | 74.7080 |