Downloads · 30 days
11
19% of all-time downloads
dianavdavidson/mms-1b-all-indic_voices-60320-hinglish_mixed_scripts-15_100-1e-4-None-steps-15000-FT
mms-1b-all-indic_voices-60320-hinglish_mixed_scripts-15_100-1e-4-None-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
11
19% of all-time downloads
All-time downloads
59
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 |
|---|---|---|---|---|
| 5.5361 | 0.6752 | 1875 | 1.2493 | 54.4309 |
| 1.4161 | 1.3504 | 3750 | 0.8843 | 44.9565 |
| 1.1511 | 2.0256 | 5625 | 0.8081 | 42.2439 |
| 1.0077 | 2.7008 | 7500 | 0.7450 | 41.3571 |
| 0.9526 | 3.3759 | 9375 | 0.7121 | 40.6139 |
| 0.9347 | 4.0511 | 11250 | 0.6875 | 39.0033 |
| 0.9039 | 4.7263 | 13125 | 0.6698 | 38.4789 |
| 0.8643 | 5.4015 | 15000 | 0.6584 | 38.2278 |