Downloads · 30 days
9
19% of all-time downloads
dianavdavidson/indicwav2vec-hindi-mucs-61959-hinglish_mixed_scripts-30_70-1e-4-steps-12000-FT
indicwav2vec-hindi-mucs-61959-hinglish_mixed_scripts-30_70-1e-4-steps-12000-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
9
19% of all-time downloads
All-time downloads
47
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 |
|---|---|---|---|---|
| 2.2231 | 0.4475 | 1000 | 1.0479 | 40.8565 |
| 1.6827 | 0.8951 | 2000 | 0.8796 | 30.9637 |
| 1.4705 | 1.3424 | 3000 | 0.8230 | 29.4994 |
| 1.3690 | 1.7899 | 4000 | 0.7649 | 27.3880 |
| 1.1338 | 2.2372 | 5000 | 0.7612 | 28.0947 |
| 1.2272 | 2.6847 | 6000 | 0.7205 | 27.7371 |
| 1.0160 | 3.1320 | 7000 | 0.7119 | 26.2813 |
| 1.0437 | 3.5795 | 8000 | 0.7003 | 25.6768 |
| 0.9566 | 4.0269 | 9000 | 0.7252 | 24.8255 |
| 0.8725 | 4.4744 | 10000 | 0.7029 | 24.5445 |
| 0.8667 | 4.9219 | 11000 | 0.7027 | 23.5570 |
| 0.6960 | 5.3692 | 12000 | 0.6887 | 26.3664 |