Downloads · 30 days
5
11% of all-time downloads
dianavdavidson/mms-1b-all-indic_voices-60320-normalized-15_100-1e-4-None-steps-15000-FT
mms-1b-all-indic_voices-60320-normalized-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
5
11% of all-time downloads
All-time downloads
47
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 |
|---|---|---|---|---|
| 4.1122 | 0.6752 | 1875 | 0.6921 | 39.6268 |
| 0.9061 | 1.3504 | 3750 | 0.5965 | 35.8300 |
| 0.8286 | 2.0256 | 5625 | 0.5597 | 34.5511 |
| 0.7666 | 2.7008 | 7500 | 0.5378 | 33.3020 |
| 0.7361 | 3.3759 | 9375 | 0.5179 | 32.7249 |
| 0.7272 | 4.0511 | 11250 | 0.5058 | 31.5111 |
| 0.7057 | 4.7263 | 13125 | 0.4945 | 30.9141 |
| 0.6809 | 5.4015 | 15000 | 0.4850 | 30.8003 |