facebookresearch/muavic
MuAViC: A Multilingual Audio-Visual Corpus for Robust Speech Recognition and Robust Speech-to-Text Translation
PythonNOASSERTION
Issues
- 3
- 1
RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format( RuntimeError: Error(s) in loading state_dict for AVHubertSeq2Seq:
#21 opened by RichardLin1999 - 0
- 0
Only audio files could be downloaded
#18 opened by ruoyxue - 2
Problem met when downloading German data
#17 opened by yiwang454 - 6
Noise parameters for decoding and training
#15 opened by roudimit - 2
- 2
- 2
Multilingual AVSR model decoding and training
#16 opened by roudimit - 2
Empty X -> EN translations
#14 opened by roudimit - 1
Unable to download corpora other than English
#11 opened by wangxuxuxuw - 1
- 3
Error when generating the manifest for AVSR
#9 opened by joyolee - 7
Error running the data prep script
#8 opened by oscarchanggoogle - 5
- 4
download_ted2020() error
#6 opened by MrSupW - 5
Got error when preparing LRS3
#5 opened by MrSupW - 1
A small bug during audio pre-processing
#3 opened by joyolee - 1
Error when preprocessing the video data
#2 opened by joyolee - 2
Minor issue
#1 opened by alkoumpa