Downloads · 30 days
7
21% of all-time downloads
dianavdavidson/indicwav2vec-hindi-vaani-62017-normalized-alldata-1e-4-epochs-50-FT
indicwav2vec-hindi-vaani-62017-normalized-alldata-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
21% of all-time downloads
All-time downloads
33
Public
Parameters
315M
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 ai4bharat/indicwav2vec-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 |
|---|---|---|---|---|
| No log | 1.0 | 270 | 1.5295 | 90.7117 |
| 7.0980 | 2.0 | 540 | 0.4651 | 31.9587 |
| 7.0980 | 3.0 | 810 | 0.3717 | 26.7604 |
| 0.9223 | 4.0 | 1080 | 0.3337 | 24.2800 |
| 0.9223 | 5.0 | 1350 | 0.3154 | 23.0888 |
| 0.7142 | 6.0 | 1620 | 0.3009 | 21.9542 |
| 0.7142 | 7.0 | 1890 | 0.2931 | 21.0758 |
| 0.6151 | 8.0 | 2160 | 0.2844 | 19.9374 |
| 0.6151 | 9.0 | 2430 | 0.2777 | 19.8206 |
| 0.5429 | 10.0 | 2700 | 0.2743 | 19.2363 |
| 0.5429 | 11.0 | 2970 | 0.2686 | 18.7085 |
| 0.4877 | 12.0 | 3240 | 0.2668 | 18.7802 |
| 0.4447 | 13.0 | 3510 | 0.2675 | 18.2109 |
| 0.4447 | 14.0 | 3780 | 0.2698 | 17.9169 |
| 0.4047 | 15.0 | 4050 | 0.2635 | 17.6191 |
| 0.4047 | 16.0 | 4320 | 0.2653 | 17.1705 |
| 0.3720 | 17.0 | 4590 | 0.2642 | 17.3251 |
| 0.3720 | 18.0 | 4860 | 0.2665 | 16.7559 |
| 0.3427 | 19.0 | 5130 | 0.2661 | 16.4732 |
| 0.3427 | 20.0 | 5400 | 0.2701 | 16.1904 |
| 0.3144 | 21.0 | 5670 | 0.2730 | 16.1490 |
| 0.3144 | 22.0 | 5940 | 0.2744 | 16.0811 |
| 0.2884 | 23.0 | 6210 | 0.2812 | 15.8813 |
| 0.2884 | 24.0 | 6480 | 0.2779 | 15.5835 |
| 0.2702 | 25.0 | 6750 | 0.2843 | 15.2744 |
| 0.2477 | 26.0 | 7020 | 0.2911 | 15.1199 |
| 0.2477 | 27.0 | 7290 | 0.2852 | 15.0483 |
| 0.2299 | 28.0 | 7560 | 0.3121 | 14.9691 |
| 0.2299 | 29.0 | 7830 | 0.2962 | 14.9804 |
| 0.2136 | 30.0 | 8100 | 0.2997 | 14.9012 |
| 0.2136 | 31.0 | 8370 | 0.3124 | 15.0143 |
| 0.2006 | 32.0 | 8640 | 0.3224 | 14.5695 |
| 0.2006 | 33.0 | 8910 | 0.3212 | 14.5997 |
| 0.1873 | 34.0 | 9180 | 0.3262 | 14.3471 |
| 0.1873 | 35.0 | 9450 | 0.3257 | 14.4112 |
| 0.1750 | 36.0 | 9720 | 0.3269 | 14.3546 |
| 0.1750 | 37.0 | 9990 | 0.3284 | 14.1586 |
| 0.1690 | 38.0 | 10260 | 0.3230 | 14.0531 |
| 0.1561 | 39.0 | 10530 | 0.3383 | 14.3471 |
| 0.1561 | 40.0 | 10800 | 0.3358 | 14.0418 |
| 0.1477 | 41.0 | 11070 | 0.3443 | 13.7779 |
| 0.1477 | 42.0 | 11340 | 0.3400 | 13.9513 |
| 0.1407 | 43.0 | 11610 | 0.3548 | 13.8307 |
| 0.1407 | 44.0 | 11880 | 0.3539 | 13.6497 |
| 0.1339 | 45.0 | 12150 | 0.3778 | 13.6610 |
| 0.1339 | 46.0 | 12420 | 0.3825 | 13.3670 |
| 0.1256 | 47.0 | 12690 | 0.3556 | 13.6083 |
| 0.1256 | 48.0 | 12960 | 0.3633 | 13.3859 |
| 0.1216 | 49.0 | 13230 | 0.3620 | 13.4009 |