Downloads · 30 days
7
12% of all-time downloads
dianavdavidson/indicwav2vec-hindi-iv_hindi_vaani-62094-hinglish_mixed_scripts-1e-4-epochs-100-FT
indicwav2vec-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
7
12% of all-time downloads
All-time downloads
58
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 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 |
|---|---|---|---|---|
| 13.1510 | 1.0 | 540 | 0.8824 | 46.5188 |
| 1.7270 | 2.0 | 1080 | 0.5516 | 31.8396 |
| 1.3322 | 3.0 | 1620 | 0.4946 | 28.8020 |
| 1.1867 | 4.0 | 2160 | 0.4693 | 27.2935 |
| 1.0824 | 5.0 | 2700 | 0.4541 | 25.9249 |
| 1.0109 | 6.0 | 3240 | 0.4443 | 25.2969 |
| 0.9578 | 7.0 | 3780 | 0.4328 | 24.8089 |
| 0.8973 | 8.0 | 4320 | 0.4265 | 24.2457 |
| 0.8556 | 9.0 | 4860 | 0.4154 | 23.6007 |
| 0.8355 | 10.0 | 5400 | 0.4192 | 23.2355 |
| 0.7887 | 11.0 | 5940 | 0.4234 | 23.0614 |
| 0.7595 | 12.0 | 6480 | 0.4313 | 22.7543 |
| 0.6976 | 13.0 | 7020 | 0.4234 | 22.6246 |
| 0.6736 | 14.0 | 7560 | 0.4097 | 22.3276 |
| 0.6482 | 15.0 | 8100 | 0.4188 | 22.1024 |
| 0.6443 | 16.0 | 8640 | 0.4349 | 21.9454 |
| 0.6096 | 17.0 | 9180 | 0.4337 | 22.1877 |
| 0.5867 | 18.0 | 9720 | 0.4298 | 21.7065 |
| 0.5837 | 19.0 | 10260 | 0.4231 | 21.8396 |
| 0.5607 | 20.0 | 10800 | 0.4552 | 21.7167 |
| 0.5298 | 21.0 | 11340 | 0.4474 | 21.8737 |