Downloads · 30 days
6
0% of all-time downloads
dianavdavidson/mms-1b-all-indic_voices-60171-hinglish_mixed_scripts-30_70-1e-4-hin-steps-10000-FT
mms-1b-all-indic_voices-60171-hinglish_mixed_scripts-30_70-1e-4-hin-steps-10000-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
6
0% of all-time downloads
All-time downloads
1.6K
Public
Parameters
965M
19.3 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 |
|---|---|---|---|---|
| 11.4840 | 2.3149 | 2000 | 2.1873 | 82.9787 |
| 7.3034 | 4.6298 | 4000 | 1.4348 | 65.7223 |
| 6.1953 | 6.9447 | 6000 | 1.2483 | 60.0333 |
| 5.5642 | 9.2593 | 8000 | 1.1259 | 56.7816 |
| 5.0449 | 11.5742 | 10000 | 0.9555 | 53.9657 |