Downloads · 30 days
6
19% of all-time downloads
dianavdavidson/wav2vec2-large-xlsr-53-iv_hindi_only-62026-hinglish_mixed_scripts-alldata-1e-4-epochs-50-FT
wav2vec2-large-xlsr-53-iv_hindi_only-62026-hinglish_mixed_scripts-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
6
19% of all-time downloads
All-time downloads
31
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 |
|---|---|---|---|---|
| 14.6794 | 1.0 | 525 | 2.9897 | 99.9968 |
| 3.3971 | 2.0 | 1050 | 0.9322 | 52.0621 |
| 2.0323 | 3.0 | 1575 | 0.7577 | 44.7351 |
| 1.6871 | 4.0 | 2100 | 0.6818 | 40.4815 |
| 1.4917 | 5.0 | 2625 | 0.6374 | 38.1402 |
| 1.3639 | 6.0 | 3150 | 0.6400 | 36.8022 |
| 1.2390 | 7.0 | 3675 | 0.6156 | 35.6221 |
| 1.1554 | 8.0 | 4200 | 0.6270 | 34.8143 |
| 1.0910 | 9.0 | 4725 | 0.6202 | 35.3791 |
| 1.0142 | 10.0 | 5250 | 0.6507 | 34.6944 |
| 0.9717 | 11.0 | 5775 | 0.6396 | 33.6657 |
| 0.9116 | 12.0 | 6300 | 0.6513 | 33.6594 |
| 0.8706 | 13.0 | 6825 | 0.6581 | 33.3817 |
| 0.8359 | 14.0 | 7350 | 0.6723 | 33.2397 |
| 0.8004 | 15.0 | 7875 | 0.6455 | 33.0693 |
| 0.7616 | 16.0 | 8400 | 0.6856 | 32.6055 |
| 0.7273 | 17.0 | 8925 | 0.6498 | 32.3593 |
| 0.6946 | 18.0 | 9450 | 0.6583 | 32.4635 |
| 0.6709 | 19.0 | 9975 | 0.6647 | 32.8579 |
| 0.6112 | 20.0 | 10500 | 0.6988 | 32.8989 |