quickvc / QuickVC-VoiceConversion

QuickVC: Any-to-many Voice Conversion Using Inverse Short-time Fourier Transform for Faster Conversion

quickvc/QuickVC-VoiceConversion Issues

48Khz Conversion
Closed 10 months ago2
Training recipe
Closed a year ago3
use_sr isn't used in the actual code
Closed a year ago7
Experiment or sample in cross-lingual setting
Closed a year ago4
Deviation from paper: mel-spec from same utterance
Closed a year ago3
Why does the system use an any-to-many configuration over a any-to-any one?
Closed a year ago1
AMP usage
Closed a year ago4
Deviation from paper: speaker encoder LSTM layer
Closed a year ago2
requirements.txt missed
Updated a year ago
Is there any pretrained model that can provided for us to test?
Closed a year ago2
Demo page fails to load in Safari
Updated a year ago
Finetuning produces silence
Closed a year ago22
Training time
Closed a year ago2
Hope that your paper will be accpeted and you will make codes published ,Thanks
Closed a year ago
Typo in paper and repository
Closed a year ago2
A question
Closed a year ago4
NICE
Closed a year ago1