r9y9 / nnmnkwii

Library to build speech synthesis systems designed for easy and fast prototyping.

https://r9y9.github.io/nnmnkwii/latest/

Autograd waveform reconstruction from STFT

r9y9 opened this issue 7 years ago · comments

Ryuichi Yamamoto commented 7 years ago

Griffin lim

Ryuichi Yamamoto commented 4 years ago

I'm closing since this feature is no longer necessary in the library. We could use PyTorch's implementation instead.

Ref: pytorch/pytorch#3775, keunwoochoi/torchaudio-contrib#27