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
First (base) checkpoint for so-vits-svc-fork
FAQ
Comments (5)
Isn't this Lora?? How can i use it?
This should be AI voice
its a svc model, as stated by the name, you can use it with vits interface that can be run in colab or local, main use case for these type of models are for voice cloning, it can be used as a part of voice changer in some voice changer client, or just as general ai singer
@wawo111 thanks !
@downloadonly thank u!