scheep
scheep
@ye2020 when you predict vocoder output ,what is your vocoder input, it's from your tacotron output mel?
my mistake! I get three cartesian coordinates, one is the listener, other is the speaker and other is the listener's attention, now I need get the input that is cartesian...
@YangangCao Have you solved it?
这个能做到实时变声吗，就是你一边说话一边改变声音，不会有卡顿或延时之类的