yl4579 / hiftnet Goto Github PK

Hi! I wanted to know if you know about Vocos and if you compared to it since it uses similar principles and has similar results.

The quality of demo samples seems to be quite good, even in noisy environments or for unseen languages. Did you use the same f0 network (pretrained on LibriTTS) for these out-of-domain experiments? I'm also wondering whether it's okay to use the F0 network as is for unseen languages. If you have any experimental insights, I'd appreciate learning about them.

Hello, yl4579. In 2.1.1. Efficient Source Generation, you do the We note that the L factor in Equation 6 scales the value by the hop size, as Equation 5 now integrates with 1/L of steps compared to steps in Equation 2.. I want to know what is the performance benefit of this change?

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

"for dr, dg" , not "for dg, dr"?

why in train.py，botch loss_disc and loss_gen use "generator_TPRLS_loss"?
loss_disc_s += generator_TPRLS_loss(y_ds_hat_r, y_ds_hat_g)
loss_gen_s += generator_TPRLS_loss(y_ds_hat_r, y_ds_hat_g)