Downloads · 30 days
8
25% of all-time downloads
dianavdavidson/indicwav2vec-hindi-vaani-61962-normalized-alldata-1e-4-steps-12000-FT
indicwav2vec-hindi-vaani-61962-normalized-alldata-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
25% of all-time downloads
All-time downloads
32
Public
Parameters
315M
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 |
|---|---|---|---|---|
| 1.2298 | 0.4631 | 1000 | 0.4929 | 33.9490 |
| 0.9360 | 0.9261 | 2000 | 0.3832 | 27.2165 |
| 0.8109 | 1.3890 | 3000 | 0.3557 | 25.2488 |
| 0.7498 | 1.8520 | 4000 | 0.3264 | 22.6892 |
| 0.6603 | 2.3149 | 5000 | 0.3156 | 21.7958 |
| 0.6593 | 2.7780 | 6000 | 0.2965 | 20.9326 |
| 0.5730 | 3.2408 | 7000 | 0.2966 | 20.1900 |
| 0.5643 | 3.7039 | 8000 | 0.2804 | 20.0957 |
| 0.4788 | 4.1667 | 9000 | 0.2860 | 18.9309 |
| 0.5125 | 4.6298 | 10000 | 0.2740 | 19.0214 |
| 0.4718 | 5.0926 | 11000 | 0.2634 | 18.4070 |
| 0.4367 | 5.5557 | 12000 | 0.2683 | 17.7661 |