Downloads · 30 days
8
18% of all-time downloads
dianavdavidson/indicwav2vec-hindi-iv_hindi_only-62073-normalized-alldata-1e-4-epochs-50-FT
indicwav2vec-hindi-iv_hindi_only-62073-normalized-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
8
18% of all-time downloads
All-time downloads
44
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 |
|---|---|---|---|---|
| 12.6228 | 1.0 | 540 | 0.7030 | 30.4579 |
| 1.6533 | 2.0 | 1080 | 0.5265 | 23.8921 |
| 1.3869 | 3.0 | 1620 | 0.4985 | 23.7473 |
| 1.3035 | 4.0 | 2160 | 0.4760 | 22.0843 |
| 1.2144 | 5.0 | 2700 | 0.4698 | 21.4345 |
| 1.1666 | 6.0 | 3240 | 0.4747 | 21.4437 |
| 1.1700 | 7.0 | 3780 | 0.4924 | 21.7918 |
| 1.1598 | 8.0 | 4320 | 0.4975 | 21.6470 |