Downloads · 30 days
7
11% of all-time downloads
dianavdavidson/indicwav2vec-hindi-iv_hindi_only-62073-hinglish_mixed_scripts-alldata-1e-4-epochs-50-FT
indicwav2vec-hindi-iv_hindi_only-62073-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
7
11% of all-time downloads
All-time downloads
66
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 |
|---|---|---|---|---|
| 14.4476 | 1.0 | 540 | 0.7442 | 32.4568 |
| 1.7083 | 2.0 | 1080 | 0.5385 | 26.4073 |
| 1.4063 | 3.0 | 1620 | 0.5166 | 25.5889 |
| 1.3097 | 4.0 | 2160 | 0.4909 | 24.0237 |
| 1.2216 | 5.0 | 2700 | 0.4752 | 23.3702 |
| 1.1640 | 6.0 | 3240 | 0.4862 | 23.3888 |
| 1.1210 | 7.0 | 3780 | 0.4744 | 23.1648 |
| 1.0690 | 8.0 | 4320 | 0.4937 | 22.9127 |
| 1.0289 | 9.0 | 4860 | 0.4733 | 23.6751 |
| 1.0191 | 10.0 | 5400 | 0.4762 | 22.6140 |
| 0.9688 | 11.0 | 5940 | 0.4803 | 22.5797 |
| 0.9456 | 12.0 | 6480 | 0.4754 | 22.8754 |
| 0.8943 | 13.0 | 7020 | 0.4885 | 22.7011 |
| 0.8702 | 14.0 | 7560 | 0.4751 | 23.0092 |