Downloads · 30 days
4
0% of all-time downloads
dianavdavidson/mms-1b-all-indic_voices-60247-hinglish_mixed_scripts-30_70-1e-4-hin-steps-15000-FT
mms-1b-all-indic_voices-60247-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
4
0% of all-time downloads
All-time downloads
2.3K
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 |
|---|---|---|---|---|
| 6.1381 | 2.1701 | 1875 | 2.5193 | 90.2678 |
| 2.4458 | 4.3403 | 3750 | 1.5296 | 68.6873 |
| 1.8332 | 6.5104 | 5625 | 1.3169 | 63.0326 |
| 1.4728 | 8.6806 | 7500 | 1.1683 | 57.0167 |
| 1.3645 | 10.8507 | 9375 | 1.0634 | 55.1987 |
| 1.2955 | 13.0208 | 11250 | 0.9573 | 52.8417 |
| 1.2053 | 15.1910 | 13125 | 0.9188 | 51.3965 |
| 1.1031 | 17.3611 | 15000 | 0.8801 | 50.5764 |