Downloads · 30 days
7
11% of all-time downloads
dianavdavidson/wav2vec2-large-xlsr-53-iv_hindi_vaani-62094-hinglish_mixed_scripts-1e-4-epochs-100-FT
wav2vec2-large-xlsr-53-iv_hindi_vaani-62094-hinglish_mixed_scripts-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
7
11% of all-time downloads
All-time downloads
61
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 |
|---|---|---|---|---|
| 13.4633 | 1.0 | 540 | 3.2369 | 100.0 |
| 3.8562 | 2.0 | 1080 | 0.8525 | 50.7031 |
| 1.6989 | 3.0 | 1620 | 0.6566 | 42.1365 |
| 1.3254 | 4.0 | 2160 | 0.5998 | 36.7372 |
| 1.1203 | 5.0 | 2700 | 0.5798 | 38.3379 |
| 0.9912 | 6.0 | 3240 | 0.5479 | 34.6280 |
| 0.8942 | 7.0 | 3780 | 0.5548 | 33.9590 |
| 0.8056 | 8.0 | 4320 | 0.5463 | 32.3515 |
| 0.7328 | 9.0 | 4860 | 0.5531 | 31.9113 |
| 0.6924 | 10.0 | 5400 | 0.5511 | 31.5017 |
| 0.6315 | 11.0 | 5940 | 0.5650 | 31.2082 |
| 0.5911 | 12.0 | 6480 | 0.5739 | 31.0239 |
| 0.5148 | 13.0 | 7020 | 0.5711 | 30.4437 |
| 0.4792 | 14.0 | 7560 | 0.5914 | 30.2833 |
| 0.4510 | 15.0 | 8100 | 0.5981 | 30.4471 |
| 0.4495 | 16.0 | 8640 | 0.6154 | 30.4061 |
| 0.4239 | 17.0 | 9180 | 0.6005 | 30.4812 |