Downloads · 30 days
5
16% of all-time downloads
dianavdavidson/wav2vec2-xls-r-1b-mucs-62255-hinglish_mixed_scripts-45_100-1e-4-epochs-100-FT
wav2vec2-xls-r-1b-mucs-62255-hinglish_mixed_scripts-45_100-1e-4-epochs-100-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 apache-2.0.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
5
16% of all-time downloads
All-time downloads
31
Public
Parameters
963M
3.9 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/wav2vec2-xls-r-1b 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 |
|---|---|---|---|---|
| No log | 1.0 | 302 | 1.2774 | 63.7462 |
| 6.7401 | 2.0 | 604 | 1.0004 | 34.9098 |
| 6.7401 | 3.0 | 906 | 0.8132 | 28.5982 |
| 1.7104 | 4.0 | 1208 | 0.7306 | 27.7475 |
| 1.1795 | 5.0 | 1510 | 0.6881 | 27.1181 |
| 1.1795 | 6.0 | 1812 | 0.7550 | 24.1579 |
| 0.9015 | 7.0 | 2114 | 0.6864 | 25.3998 |
| 0.9015 | 8.0 | 2416 | 0.6610 | 24.6853 |
| 0.7415 | 9.0 | 2718 | 0.7550 | 23.3243 |
| 0.6035 | 10.0 | 3020 | 0.7270 | 24.5832 |
| 0.6035 | 11.0 | 3322 | 0.7331 | 22.6097 |
| 0.4859 | 12.0 | 3624 | 0.7455 | 22.5247 |
| 0.4859 | 13.0 | 3926 | 0.7559 | 22.6438 |
| 0.4226 | 14.0 | 4228 | 0.7775 | 22.4396 |
| 0.3582 | 15.0 | 4530 | 0.7717 | 22.0653 |
| 0.3582 | 16.0 | 4832 | 0.8452 | 21.6570 |
| 0.2961 | 17.0 | 5134 | 0.7986 | 20.3471 |
| 0.2961 | 18.0 | 5436 | 0.8261 | 21.2657 |
| 0.2601 | 19.0 | 5738 | 0.8047 | 22.3205 |
| 0.2281 | 20.0 | 6040 | 0.9148 | 20.8744 |