Downloads · 30 days
4
4% of all-time downloads
dianavdavidson/wh_small_iv_no_lg_id_indic_voices_52031_trial
wh_small_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
4
4% of all-time downloads
All-time downloads
100
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 |
|---|---|---|---|---|
| 1.1045 | 0.0110 | 50 | 0.8920 | 82.9863 |
| 0.6137 | 0.0220 | 100 | 0.6698 | 69.5277 |
| 0.6053 | 0.0330 | 150 | 0.5969 | 62.6714 |
| 0.4919 | 0.0440 | 200 | 0.5578 | 64.7537 |
| 0.4791 | 0.0550 | 250 | 0.5506 | 60.7415 |
| 0.4945 | 0.0660 | 300 | 0.5125 | 56.1706 |
| 0.5037 | 0.0770 | 350 | 0.4956 | 57.1356 |
| 0.4886 | 0.0880 | 400 | 0.4739 | 52.2600 |
| 0.4683 | 0.0990 | 450 | 0.4567 | 57.0340 |
| 0.4015 | 0.1100 | 500 | 0.4376 | 58.0498 |