Downloads · 30 days
8
17% of all-time downloads
dianavdavidson/indicwav2vec-hindi-mucs-61961-hinglish_mixed_scripts-15_100-1e-4-steps-12000-FT
indicwav2vec-hindi-mucs-61961-hinglish_mixed_scripts-15_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
17% of all-time downloads
All-time downloads
47
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 |
|---|---|---|---|---|
| 2.3203 | 0.2297 | 1000 | 1.2108 | 44.7264 |
| 1.8187 | 0.4594 | 2000 | 1.0292 | 35.2718 |
| 1.6584 | 0.6891 | 3000 | 0.9731 | 34.6838 |
| 1.8298 | 0.9188 | 4000 | 0.9215 | 32.0076 |
| 1.8085 | 1.1484 | 5000 | 0.8959 | 30.5167 |
| 1.4925 | 1.3781 | 6000 | 0.8941 | 30.1926 |
| 1.3773 | 1.6078 | 7000 | 0.8770 | 29.3407 |
| 1.3095 | 1.8375 | 8000 | 0.8580 | 28.6415 |
| 1.1520 | 2.0671 | 9000 | 0.8495 | 28.7897 |
| 1.4421 | 2.2968 | 10000 | 0.8473 | 26.9701 |
| 1.1862 | 2.5265 | 11000 | 0.8434 | 26.3126 |
| 1.2270 | 2.7562 | 12000 | 0.8255 | 27.6183 |