Downloads · 30 days
6
14% of all-time downloads
dianavdavidson/wav2vec2-large-xlsr-53-iv_hindi_vaani-62420-hinglish_mixed_scripts-alldata-1e-4-100-mix-0.9-FT
wav2vec2-large-xlsr-53-iv_hindi_vaani-62420-hinglish_mixed_scripts-alldata-1e-4-100-mix-0.9-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
6
14% of all-time downloads
All-time downloads
42
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 facebook/wav2vec2-large-xlsr-53 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 |
|---|---|---|---|---|
| 4.9064 | 1.0 | 1080 | 1.4185 | 69.8870 |
| 1.9841 | 2.0 | 2160 | 0.8610 | 47.5973 |
| 1.3591 | 3.0 | 3240 | 0.8121 | 42.7447 |
| 1.0169 | 4.0 | 4320 | 0.8096 | 41.0744 |
| 0.8285 | 5.0 | 5400 | 0.8332 | 40.4425 |
| 0.6837 | 6.0 | 6480 | 0.8754 | 39.4817 |
| 0.5525 | 7.0 | 7560 | 0.9150 | 39.1239 |
| 0.4859 | 8.0 | 8640 | 0.9432 | 38.3062 |
| 0.4183 | 9.0 | 9720 | 1.0076 | 39.5441 |
| 0.3664 | 10.0 | 10800 | 0.9633 | 38.5544 |
| 0.3223 | 11.0 | 11880 | 0.9984 | 37.8403 |
| 0.3005 | 12.0 | 12960 | 1.0147 | 38.1418 |
| 0.2779 | 13.0 | 14040 | 1.0707 | 37.4657 |
| 0.2416 | 14.0 | 15120 | 1.0736 | 37.3043 |
| 0.2356 | 15.0 | 16200 | 1.1175 | 37.8083 |
| 0.2170 | 16.0 | 17280 | 1.1906 | 37.6180 |
| 0.1897 | 17.0 | 18360 | 1.0856 | 37.5556 |