Downloads · 30 days
6
0% of all-time downloads
dianavdavidson/mms-1b-all-indic_voices-normalized-30_70-lg-hin-steps-10000-lr-0.0001-FT
mms-1b-all-indic_voices-normalized-30_70-lg-hin-steps-10000-lr-0.0001-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
2K
Public
Parameters
965M
61.7 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 |
|---|---|---|---|---|
| 5.7174 | 1.4468 | 1250 | 0.8496 | 51.0400 |
| 1.2191 | 2.8935 | 2500 | 0.6867 | 42.5026 |
| 1.0813 | 4.3403 | 3750 | 0.6342 | 41.2759 |
| 0.9566 | 5.7870 | 5000 | 0.5972 | 38.5769 |
| 0.9329 | 7.2338 | 6250 | 0.5759 | 38.0304 |
| 0.9019 | 8.6806 | 7500 | 0.5605 | 37.7182 |
| 0.8811 | 10.1273 | 8750 | 0.5465 | 36.5583 |
| 0.8498 | 11.5741 | 10000 | 0.5356 | 36.0899 |