TurkicASR icon indicating copy to clipboard operation
TurkicASR copied to clipboard

Published 20 hours ago • verified publisher icon IS2AI
→

Metadata

A multilingual ASR model that can recognize ten Turkic languages—Azerbaijani, Bashkir, Chuvash, Kazakh, Kyrgyz, Sakha, Tatar, Turkish, Uyghur, and Uzbek.

Results 2 TurkicASR issues
Sort by recently updated
recently updated
newest added

running error

1 comment

When I run recognize.py, I got the following error: WARNING:root:Using legacy_rel_pos and it will be deprecated in the future. WARNING:root:Using legacy_rel_selfattn and it will be deprecated in the future. /home/heyayun/anaconda3/envs/turkic/lib/python3.9/site-packages/torch/functional.py:641:...

h310558606 avatar h310558606

How to force language of ASR?

I have dataset with Uzbek audios. But sometimes model predicts as [tr] or even [ru]. How can I force model to make prediction as [uz] language?

elch10 avatar elch10

← Metadata

54
Stars
7
Forks
Watchers

Owner

verified publisher icon IS2AI

Metadata

A multilingual ASR model that can recognize ten Turkic languages—Azerbaijani, Bashkir, Chuvash, Kazakh, Kyrgyz, Sakha, Tatar, Turkish, Uyghur, and Uzbek.

Back