HiFiplusplus-pytorch
HiFiplusplus-pytorch copied to clipboard
which is better for TTS, hifigan vs hifi++?
which is better for TTS, hifigan vs hifi++?
right now I guess iSTFTNet is best compared to both hifigan and hifi++. Currently, I am struggling to implement hifi++ architecture correctly. The author didn't share much info regarding training hyperparameters thats why this hifi++ implementation underperform compared to original hifigan
Thank very much for you reply, I will try to train iSTFTNet for TTS.