A more accurate English Model Introduction

[jerryli27]

I found the English description a bit hard to understand. The English version missed the crucial part that you use VITS. The 中文简体 intro is easier to understand.

... to extract source audio speech features, and inputs them together with F0 to replace the original text input to achieve the effect of song conversion. ...

The following would be better in my humble opinion:

... to extract source audio speech features, and inputs them together with F0 into VITS instead of the original text input to achieve the effect of song conversion. ...

Thanks!

P.S. Sorry, no 中文简体 input method on this laptop, so I'm using English.

[Kerushii]

"The vectors are directly fed into VITS instead of converting to a text based intermediate; thus the pitch and intonations are conserved"