Downloads · 30 days
12
1% of all-time downloads
dianavdavidson/mms-1b-all-indic_voices-60250-hinglish_mixed_scripts-30_70-1e-4-hin-steps-15000-FT
mms-1b-all-indic_voices-60250-hinglish_mixed_scripts-30_70-1e-4-hin-steps-15000-FT 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 cc-by-nc-4.0.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
12
1% of all-time downloads
All-time downloads
2.2K
Public
Parameters
965M
30.9 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors3.9 GB · 100%
From the Hugging Face model README
This model is a fine-tuned version of facebook/mms-1b-all 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 |
|---|---|---|---|---|
| 6.1454 | 2.1701 | 1875 | 2.5217 | 89.9925 |
| 2.4414 | 4.3403 | 3750 | 1.5215 | 68.7905 |
| 1.8268 | 6.5104 | 5625 | 1.3085 | 62.3100 |
| 1.4655 | 8.6806 | 7500 | 1.1665 | 57.4181 |
| 1.3350 | 10.8507 | 9375 | 0.9775 | 55.3822 |
| 1.2499 | 13.0208 | 11250 | 0.9273 | 51.5513 |
| 1.1806 | 15.1910 | 13125 | 0.8930 | 51.0581 |
| 1.0805 | 17.3611 | 15000 | 0.8204 | 49.4867 |