Downloads · 30 days
5
15% of all-time downloads
dianavdavidson/wav2vec2-xls-r-1b-mucs-62241-hinglish_mixed_scripts-1e-4-epochs-100-FT
wav2vec2-xls-r-1b-mucs-62241-hinglish_mixed_scripts-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
15% of all-time downloads
All-time downloads
34
Public
Parameters
963M
7.7 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/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 | 440 | 1.1864 | 55.5519 |
| 5.8287 | 2.0 | 880 | 0.9958 | 46.6710 |
| 1.5077 | 3.0 | 1320 | 0.8929 | 31.6334 |
| 1.1644 | 4.0 | 1760 | 0.8188 | 30.3585 |
| 1.0054 | 5.0 | 2200 | 0.7818 | 30.0207 |
| 0.8707 | 6.0 | 2640 | 0.7738 | 27.6888 |
| 0.7667 | 7.0 | 3080 | 0.7376 | 31.0341 |
| 0.6749 | 8.0 | 3520 | 0.7262 | 26.3594 |
| 0.6749 | 9.0 | 3960 | 0.7739 | 26.7081 |
| 0.5923 | 10.0 | 4400 | 0.7761 | 25.2479 |
| 0.5269 | 11.0 | 4840 | 0.7695 | 24.1364 |
| 0.4626 | 12.0 | 5280 | 0.7458 | 25.0300 |
| 0.4132 | 13.0 | 5720 | 0.7616 | 24.2781 |
| 0.3438 | 14.0 | 6160 | 0.7887 | 25.3569 |