Lil Peep (2017)
RVC v2400 epochsArtistEnglish

📣

From the creator

"Uses about 40 minutes worth of raw dry vocals from stems from 2017"

Description

Introducing the Lil Peep (2017) (RVC 2) 400 Epochs - a state-of-the-art AI Voice Model developed by Weights using Retrieval-Based Voice Conversion (RVC) technology. This innovative model has been trained on approximately 40 minutes of raw dry vocals sourced from Lil Peep's 2017 stems, enabling it to generate stunningly authentic and emotive vocal performances. With its advanced capabilities, users can now create AI covers and text-to-speech outputs that capture the unique sound and style of Lil Peep's music like never before. Optimized for SEO, this model offers unparalleled accessibility and creative possibilities for musicians, producers, and artists alike. Take advantage of our cutting-edge AI tools today and start creating your own AI covers or transforming text into speech – all for free!

See more

Weekly Metrics

Samples

New
Classic
Speaking

Pitch

0

#1

Male

Singing

🇺🇸 English

#2

Female

Singing

🇺🇸 English

#3

Female

Singing (Dry)

🇺🇸 English

#4

Female

Singing (High)

🇺🇸 English

#5

Male

Singing 2

🇺🇸 English

#6

Male

Singing (Dry)

🇺🇸 English

#7

Male

Singing (Dry, High)

🇺🇸 English

User Creations

Not certified by Weights

"No importa las veces que me vea al espejo, Sigo sin amar ese hombre, me siento tan viejo. Algunas personas no estamos para elegir, Madre, por qué me abandonaste, quiero saber por qué. Será que también me estés buscando, A veces me siento tan confundido, me estoy quebrando. Ya no te cuento nada, no sé cómo ayudarme, Reprimo mis emociones, no sé qué hacer para calmarme."

Model Files

Compressed File Verified

Lil Peep (2017).zip

md5: 55629038f7c1b78cfc70eed8bfa4cf9e

Individual Files Verified

model.index

md5: f602c293e3e6680ad3a2169755b2332e

205.28 MB

model.pth

md5: 2e62afe356b44536ffe9afe86b520c01

52.67 MB

Comments

Demo:

Audio removed in response to copyright claim.

^ 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?

can you send me the song u used in dms?

for the input? or dataset

Audio removed in response to copyright claim.

Add a comment

Post
Selected Audio
Selected Audio