Intro
In this model has all the character, can achieve higher pitch. Gotou Futari is the cutest voice and able produce higher output quality even just 10 files at ~10 seconds each, Male Voice to Gotou Futari need to Crepe +6 pitch (0.5 octave) transpose (adjust depending how deep source is). Sample AI song are down below.
Dataset
Source dataset is from streaming services, model quality hard to achieve due to lossy codec (MP3/AAC/Opus), perhaps waiting BD Remux/FLAC release and rip from there, so processing, clean-up will be much better than ripping from the web
Infer
It has usual so-vits-svc-fork and rvc, I not sure which one is good, but rvc train much quicker but still artifact at breathing/whisper/low loudness
Post Processing
EffectPresets.xml included inside v2.1 zip file, read the readme.txt file please
Sample Song
Hyper Act. - Harapan ft. Nijika Ijichi
Language: ms-MY (Bahasa Melayu) [so-vits-svc-fork]
Kiroro - Mirai e by Hiroi Kikuri
Language: ja-JP (Japanese) [so-vits-svc-fork]
Description
Added Gotou Futari, enjoy her cute voice ♥
FAQ
Comments (7)
hello, do you have some good f0 method choice to get good result?
do you mean training parameter and settings?
@Anime4000 yes like that, also i need any recommendations which should i use(dio, crepe, harvest, etc)
@Elaina617 use UVR to get vocal only then DeEcho & DeReverb.
I always use crepe, has better pitch estimation.
Male Voice to Pitch
Gotou Futari = +6
Hiroi Kikuri = +1
Ijichi Seika = +1
Others = +4
for the pitch, still need manual detect how close to original VA
@Anime4000 i want to ask for rvc version, did you use rvc 2.0?
@Elaina617 RVC Beta @ "lj1995/VoiceConversionWebUI"
@Elaina617 yea, I train on v2