Downloads · 30 days
2
2% of all-time downloads
dianavdavidson/wh_med_iv_no_lg_id_indic_voices_52031_trial
wh_med_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
2
2% of all-time downloads
All-time downloads
86
Public
Parameters
764M
15.3 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors3.1 GB · 100%
From the Hugging Face model README
This model is a fine-tuned version of openai/whisper-medium 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 |
|---|---|---|---|---|
| 2.1591 | 0.0110 | 50 | 1.7316 | 68.0549 |
| 0.8792 | 0.0220 | 100 | 0.8593 | 115.5409 |
| 0.4374 | 0.0330 | 150 | 0.4368 | 67.3946 |
| 0.3813 | 0.0440 | 200 | 0.4053 | 55.5612 |
| 0.3548 | 0.0550 | 250 | 0.4068 | 51.8537 |
| 0.3764 | 0.0660 | 300 | 0.3826 | 56.0691 |
| 0.3829 | 0.0770 | 350 | 0.3718 | 72.0670 |
| 0.4039 | 0.0880 | 400 | 0.3554 | 63.9411 |
| 0.3387 | 0.0990 | 450 | 0.3642 | 86.1351 |
| 0.2871 | 0.1100 | 500 | 0.3459 | 90.9091 |