microsoft / UniSpeech

UniSpeech - Large Scale Self-Supervised Learning for Speech
Other
406 stars 71 forks source link

UniSpeech-SAT/speaker_verification: torchaudio version #17

Closed msh9184 closed 2 years ago

msh9184 commented 2 years ago

Hello, In UniSpeech-SAT/speaker_verification/verification.py file, resample function of torchaudio.functional seems to be only supported from torchaudio version 0.9.0 or higher. For the versions below 0.9.0, there seems to be Resample function of torchaudio.transforms. Thanks.

czy97 commented 2 years ago

Hello, In UniSpeech-SAT/speaker_verification/verification.py file, resample function of torchaudio.functional seems to be only supported from torchaudio version 0.9.0 or higher. For the versions below 0.9.0, there seems to be Resample function of torchaudio.transforms. Thanks.

Thanks for the comment, I have updated the code to be compatible with old torchaudio versions.