Downloads · 30 days
8
14% of all-time downloads
dianavdavidson/wav2vec2-large-xlsr-hindi-iv_hindi_vaani-62094-hinglish_mixed_scripts-1e-4-epochs-100-FT
wav2vec2-large-xlsr-hindi-iv_hindi_vaani-62094-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
8
14% of all-time downloads
All-time downloads
59
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 skylord/wav2vec2-large-xlsr-hindi 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 |
|---|---|---|---|---|
| 11.4242 | 1.0 | 540 | 1.3510 | 70.7884 |
| 2.4335 | 2.0 | 1080 | 0.7777 | 47.2116 |
| 1.7499 | 3.0 | 1620 | 0.6635 | 40.3276 |
| 1.4725 | 4.0 | 2160 | 0.5943 | 36.3447 |
| 1.2802 | 5.0 | 2700 | 0.5583 | 34.6758 |
| 1.1540 | 6.0 | 3240 | 0.5461 | 33.0205 |
| 1.0723 | 7.0 | 3780 | 0.5499 | 32.1980 |
| 0.9882 | 8.0 | 4320 | 0.5409 | 31.3720 |
| 0.9113 | 9.0 | 4860 | 0.5315 | 30.8532 |
| 0.8655 | 10.0 | 5400 | 0.5207 | 29.5392 |
| 0.7974 | 11.0 | 5940 | 0.5271 | 29.3857 |
| 0.7537 | 12.0 | 6480 | 0.5464 | 29.4232 |
| 0.6608 | 13.0 | 7020 | 0.5497 | 28.7133 |
| 0.6318 | 14.0 | 7560 | 0.5527 | 28.3549 |
| 0.5780 | 15.0 | 8100 | 0.5486 | 28.2696 |
| 0.5778 | 16.0 | 8640 | 0.5919 | 28.2048 |
| 0.5395 | 17.0 | 9180 | 0.5846 | 27.9829 |
| 0.5041 | 18.0 | 9720 | 0.5997 | 27.7065 |
| 0.4977 | 19.0 | 10260 | 0.6145 | 27.8771 |
| 0.4849 | 20.0 | 10800 | 0.5862 | 27.6792 |
| 0.4421 | 21.0 | 11340 | 0.6277 | 27.6280 |
| 0.4368 | 22.0 | 11880 | 0.6146 | 27.5051 |
| 0.4095 | 23.0 | 12420 | 0.6494 | 27.7509 |
| 0.3930 | 24.0 | 12960 | 0.6456 | 27.2628 |
| 0.3657 | 25.0 | 13500 | 0.6767 | 27.2014 |
| 0.3580 | 26.0 | 14040 | 0.6183 | 26.9454 |
| 0.3377 | 27.0 | 14580 | 0.6580 | 27.0819 |
| 0.3367 | 28.0 | 15120 | 0.6411 | 27.0239 |
| 0.3241 | 29.0 | 15660 | 0.6794 | 26.8601 |
| 0.3124 | 30.0 | 16200 | 0.6727 | 26.7235 |
| 0.3113 | 31.0 | 16740 | 0.6857 | 26.7986 |
| 0.2953 | 32.0 | 17280 | 0.6855 | 26.8157 |
| 0.2831 | 33.0 | 17820 | 0.6632 | 26.8737 |