Downloads · 30 days
8
22% of all-time downloads
dianavdavidson/wav2vec2-large-xlsr-hindi-vaani-62080-normalized-alldata-1e-4-epochs-100-FT
wav2vec2-large-xlsr-hindi-vaani-62080-normalized-alldata-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
22% of all-time downloads
All-time downloads
37
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 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 |
|---|---|---|---|---|
| 6.1476 | 1.0 | 540 | 0.6554 | 47.0974 |
| 1.2585 | 2.0 | 1080 | 0.3919 | 28.6716 |
| 0.8365 | 3.0 | 1620 | 0.3278 | 23.2057 |
| 0.6518 | 4.0 | 2160 | 0.2983 | 21.5998 |
| 0.5464 | 5.0 | 2700 | 0.2798 | 19.6736 |
| 0.4696 | 6.0 | 3240 | 0.2843 | 19.7716 |
| 0.4091 | 7.0 | 3780 | 0.2757 | 17.7624 |
| 0.3662 | 8.0 | 4320 | 0.2825 | 16.8954 |
| 0.3210 | 9.0 | 4860 | 0.2909 | 17.0424 |
| 0.2940 | 10.0 | 5400 | 0.2964 | 16.3601 |
| 0.2637 | 11.0 | 5940 | 0.2980 | 15.5081 |
| 0.2405 | 12.0 | 6480 | 0.2921 | 15.1350 |
| 0.2008 | 13.0 | 7020 | 0.3090 | 15.2443 |
| 0.1843 | 14.0 | 7560 | 0.3289 | 15.0558 |
| 0.1730 | 15.0 | 8100 | 0.3218 | 14.1134 |
| 0.1589 | 16.0 | 8640 | 0.3391 | 14.2378 |
| 0.1489 | 17.0 | 9180 | 0.3427 | 13.8005 |
| 0.1448 | 18.0 | 9720 | 0.3333 | 13.9475 |
| 0.1319 | 19.0 | 10260 | 0.3542 | 13.9136 |
| 0.1264 | 20.0 | 10800 | 0.3531 | 13.7779 |
| 0.1243 | 21.0 | 11340 | 0.3600 | 13.9324 |
| 0.1153 | 22.0 | 11880 | 0.3585 | 13.6535 |
| 0.1093 | 23.0 | 12420 | 0.3623 | 13.6799 |
| 0.1086 | 24.0 | 12960 | 0.3743 | 13.6271 |
| 0.0974 | 25.0 | 13500 | 0.3585 | 13.7892 |
| 0.0974 | 26.0 | 14040 | 0.3640 | 13.2690 |
| 0.0937 | 27.0 | 14580 | 0.3660 | 13.0654 |
| 0.0915 | 28.0 | 15120 | 0.3977 | 13.2200 |
| 0.0883 | 29.0 | 15660 | 0.3836 | 13.1672 |
| 0.0855 | 30.0 | 16200 | 0.3696 | 13.0918 |