Downloads · 30 days
8
19% of all-time downloads
dianavdavidson/indicwav2vec-hindi-mucs-61961-hinglish_mixed_scripts-5_100-1e-4-steps-12000-FT
indicwav2vec-hindi-mucs-61961-hinglish_mixed_scripts-5_100-1e-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
8
19% of all-time downloads
All-time downloads
42
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 |
|---|---|---|---|---|
| 2.2897 | 0.1860 | 1000 | 1.2834 | 46.5183 |
| 1.9068 | 0.3720 | 2000 | 1.1069 | 37.6071 |
| 1.7717 | 0.5579 | 3000 | 1.0290 | 37.1427 |
| 1.6491 | 0.7439 | 4000 | 1.0040 | 33.9778 |
| 1.6340 | 0.9299 | 5000 | 0.9584 | 34.6619 |
| 1.3977 | 1.1159 | 6000 | 0.9817 | 32.0300 |
| 1.4147 | 1.3018 | 7000 | 0.9865 | 31.6519 |
| 1.4738 | 1.4878 | 8000 | 0.9576 | 30.8670 |
| 1.3468 | 1.6738 | 9000 | 0.9697 | 31.2775 |
| 1.3324 | 1.8598 | 10000 | 0.9206 | 31.5439 |
| 1.1794 | 2.0458 | 11000 | 0.9889 | 29.5384 |
| 1.1645 | 2.2317 | 12000 | 0.9436 | 30.2405 |