Downloads · 30 days
39
24% of all-time downloads
dianavdavidson/wav2vec2-large-xlsr-53-iv_hindi_vaani-62420-hinglish_mixed_scripts-alldata-1e-4-100-mix-0.1-FT
wav2vec2-large-xlsr-53-iv_hindi_vaani-62420-hinglish_mixed_scripts-alldata-1e-4-100-mix-0.1-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
39
24% of all-time downloads
All-time downloads
160
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 |
|---|---|---|---|---|
| 2.6284 | 1.0 | 1080 | 0.7464 | 40.3228 |
| 1.0407 | 2.0 | 2160 | 0.4660 | 30.2183 |
| 0.6285 | 3.0 | 3240 | 0.4367 | 26.8265 |
| 0.4453 | 4.0 | 4320 | 0.4654 | 24.9845 |
| 0.3249 | 5.0 | 5400 | 0.4674 | 23.4127 |
| 0.2503 | 6.0 | 6480 | 0.5044 | 24.1685 |
| 0.1731 | 7.0 | 7560 | 0.5203 | 23.3433 |
| 0.1501 | 8.0 | 8640 | 0.5235 | 22.7336 |
| 0.1351 | 9.0 | 9720 | 0.5713 | 22.4451 |
| 0.1242 | 10.0 | 10800 | 0.5989 | 23.1699 |
| 0.1066 | 11.0 | 11880 | 0.5605 | 22.4378 |
| 0.0944 | 12.0 | 12960 | 0.5812 | 22.4196 |
| 0.0770 | 13.0 | 14040 | 0.5857 | 22.4744 |
| 0.0759 | 14.0 | 15120 | 0.5776 | 22.3393 |
| 0.0701 | 15.0 | 16200 | 0.5947 | 21.7788 |
| 0.0722 | 16.0 | 17280 | 0.6501 | 22.1877 |
| 0.0642 | 17.0 | 18360 | 0.6070 | 21.7825 |
| 0.0590 | 18.0 | 19440 | 0.6210 | 22.2936 |