Downloads · 30 days
7
26% of all-time downloads
dianavdavidson/wav2vec2-large-xlsr-53-mucs-62026-hinglish_mixed_scripts-25_45-1e-4-epochs-50-FT
wav2vec2-large-xlsr-53-mucs-62026-hinglish_mixed_scripts-25_45-1e-4-epochs-50-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
7
26% of all-time downloads
All-time downloads
27
Public
Parameters
316M
1.3 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors1.3 GB · 100%
From the Hugging Face model README
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 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 | 3.6496 | 100.0 |
| 15.6440 | 2.0 | 880 | 1.3817 | 61.3817 |
| 3.9684 | 3.0 | 1320 | 1.0064 | 39.2176 |
| 1.5915 | 4.0 | 1760 | 0.9114 | 35.6979 |
| 1.1706 | 5.0 | 2200 | 0.8666 | 35.8396 |
| 0.9292 | 6.0 | 2640 | 0.8515 | 30.0207 |
| 0.7762 | 7.0 | 3080 | 0.8498 | 31.0232 |
| 0.6651 | 8.0 | 3520 | 0.9066 | 28.5278 |
| 0.6651 | 9.0 | 3960 | 0.8544 | 28.6477 |
| 0.5757 | 10.0 | 4400 | 0.8615 | 28.7022 |
| 0.5002 | 11.0 | 4840 | 0.9317 | 27.4273 |
| 0.4427 | 12.0 | 5280 | 0.9322 | 27.0241 |
| 0.3973 | 13.0 | 5720 | 0.9493 | 27.6779 |
| 0.3328 | 14.0 | 6160 | 0.9744 | 26.6754 |
| 0.3045 | 15.0 | 6600 | 0.9299 | 27.2965 |
| 0.2630 | 16.0 | 7040 | 0.9698 | 25.0082 |
| 0.2630 | 17.0 | 7480 | 1.0238 | 25.4876 |
| 0.2275 | 18.0 | 7920 | 1.0258 | 24.7031 |
| 0.1971 | 19.0 | 8360 | 1.0368 | 25.4440 |
| 0.1787 | 20.0 | 8800 | 1.0750 | 25.4223 |
| 0.1696 | 21.0 | 9240 | 0.9830 | 25.1171 |