Downloads · 30 days
5
24% of all-time downloads
dianavdavidson/wav2vec2-large-xlsr-53-indic_voices-61867-hinglish_mixed_scripts-30_70-1e-4-steps-12000-FT
wav2vec2-large-xlsr-53-indic_voices-61867-hinglish_mixed_scripts-30_70-1e-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
5
24% of all-time downloads
All-time downloads
21
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 |
|---|---|---|---|---|
| 6.8738 | 0.6944 | 600 | 3.2733 | 99.9943 |
| 3.4480 | 1.3889 | 1200 | 1.4232 | 77.7083 |
| 2.5729 | 2.0833 | 1800 | 1.0742 | 66.9324 |
| 2.2622 | 2.7778 | 2400 | 0.9639 | 62.0520 |
| 1.9112 | 3.4722 | 3000 | 0.9155 | 59.5974 |
| 1.6652 | 4.1667 | 3600 | 0.8738 | 56.8160 |
| 1.6760 | 4.8611 | 4200 | 0.8282 | 54.2754 |
| 1.5318 | 5.5556 | 4800 | 0.8268 | 54.9292 |
| 1.4113 | 6.25 | 5400 | 0.8493 | 53.6790 |
| 1.3732 | 6.9444 | 6000 | 0.8071 | 53.4840 |
| 1.2668 | 7.6389 | 6600 | 0.8075 | 51.1097 |
| 1.2021 | 8.3333 | 7200 | 0.8337 | 51.5341 |
| 1.1680 | 9.0278 | 7800 | 0.8266 | 51.4825 |
| 1.1184 | 9.7222 | 8400 | 0.8347 | 51.7004 |