HiFTNet
HiFTNet copied to clipboard
yl4579
HiFTNet: A Fast High-Quality Neural Vocoder with Harmonic-plus-Noise Filter and Inverse Short Time Fourier Transform
Thanks for your greak work I got warnings when torch==1.8 and 1.10 （Under 1.8 will return error about return_complex of torch） ``` UserWarning: The default behavior for interpolate/upsample with float...
Hi! I wanted to know if you know about [Vocos](https://arxiv.org/abs/2306.00814) and if you compared to it since it uses similar principles and has similar results.
Hi, thx for your great work! I wonder is it possible to add multi band to further improve inference speed like https://github.com/MasayaKawamura/MB-iSTFT-VITS
Hi, If I want to train the F0 model from scratch in the other repo, do I need to train the JDC with a 22k sampling rate in order to...
When I go to train the vocoder with the song data, I get a situation of nan, is there a recommended configuration for training the song vocoder. 
Hi, are you able to tell me if I can use your vocoder with vits (https://github.com/jaywalnut310/vits)? Are you able to tell me if your vocoder has better quality than the...
While the attempt to use iSTFT to avoid upscaling artifacts introduced by last two upscales in HiFiGAN is commendable, it just does not work. On a single sample the model...
