Description
< Uses about 40 minutes worth of raw, dry vocals from stems from 2017
Comments

^ Just some random Juice WRLD outtake lmao

Juice WRLD's voice works weirdly well for most artists

how do u clean ur dataset?

Noise gate, sometimes eq if there's major mic bleed

no truncating silence or/and de noise?

oh I thought you just meant the audio itself lmao

yeah I truncate any silences, and use denoise if I can audibly hear noise

if not I don't see a point

it'll just cause vocal loss

well i dunno i can hear some stuff when the model deals with silence

like some weird clicking

it'll just be where he hit the mic or something and a noise gate didn't catch it out

or room tone

it's using raw vocals so there's no UVR stuff happening

good did u train 40k?

yeah

hmm weird

can you send me the song u used in dms?

for the input? or dataset

input
Add a comment
Samples
Pitch
More to explore
Saiba Momoi (Blue Archive)

Ariana Grande AI

JENNIE of BLACKPINK [Strong Ver.]

Saiba Momoi (Blue Archive) (VA: Tokui Sora)

Hatsune Miku
SpongeBob SquarePants (Talking And Singing)
Takanashi Hoshino (from Blue Archive)

Satoru Gojo (JJK) [VA Yuichi Nakamura]

ENHYPEN Heeseung

Sunaokami Shiroko (Blue Archive)

Villager (Minecraft)

Mortis [Brawl stars]
Jungkook (BTS)

Tendou Arisu (Blue Archive)

Kanye West
Loading more