Downloads · 30 days
8
21% of all-time downloads
dianavdavidson/indicwav2vec-hindi-iv_hindi_only-62079-normalized-alldata-1e-4-epochs-100-FT
indicwav2vec-hindi-iv_hindi_only-62079-normalized-alldata-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
8
21% of all-time downloads
All-time downloads
39
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 |
|---|---|---|---|---|
| 12.6192 | 1.0 | 540 | 0.6907 | 28.7580 |
| 1.6490 | 2.0 | 1080 | 0.5128 | 24.2493 |
| 1.3840 | 3.0 | 1620 | 0.5113 | 23.5687 |
| 1.2864 | 4.0 | 2160 | 0.4820 | 21.8503 |
| 1.2053 | 5.0 | 2700 | 0.4680 | 21.6193 |
| 1.1688 | 6.0 | 3240 | 0.4901 | 21.9642 |
| 1.1624 | 7.0 | 3780 | 0.4895 | 21.4992 |
| 1.1487 | 8.0 | 4320 | 0.5104 | 21.5023 |
| 1.1937 | 9.0 | 4860 | 0.5941 | 25.9031 |
| 1.4056 | 10.0 | 5400 | nan | 85.8428 |