Name: Pusha T (Daytona Era Clean Vocals) | AI RVC Model
Brand: Weights
Rating: 4.4 (3 reviews)

Introducing the "Pusha T (Daytona Era Clean Vocals)" AI Voice model, an epitome of modern AI Music, refined with clean Daytona session vocals for extraordinary audio experiences. This innovative RVC Model, developed by Weights, gifts you an unprecedented 15 minutes of pristine, unmixed vocals, tuned perfectly to the Daytona Era of Pusha T's discography. The model undergoes an exhaustive learning process with 500 epochs and around 31k steps, ensuring unparalleled accuracy in capturing its unique musical essence. The crepe hop length, set at 50, further enhances the model's superior voice conversion performance. With this AI Voice Model, you can effortlessly create AI Covers, thereby lending a distinct texture to your music, imbued by the iconic Pusha T (Daytona Era Clean Vocals). Dive into the world of AI music today and create text-to-speech renderings or AI covers using our free AI tools. Explore the limitless potentials of voice conversion with Weights, and unlock a whole new realm of musical creativity.

How my vocals are clean is because i got Clean Daytona Session vocals, and also the vocals are unmixed. But the dataset is 15 min set at crepe hop length - 50, and the epochs is 500 at 31K steps

Pusha T (Daytona Era Clean Vocals)

Cracked_Fl

Guntrell RB

TITAN Pretrained 40khz :50 Batch Size: 4 Sample Rate Cutoff 39Khz some RX11 on the crackle part of Higgs.

Frank Ocean Endless Era

Frank Ocean Endless Era (RVC V2, RMVPE, 456 Epochs)

:59 I know it's not much but it's sounds pretty accurate The Batch Size is set at 2. Pretrain: Original Sample Rate - 40khz and the cutoff is 39 Download

Yellow Pearl From Steven Universe

Yellow Pearl From Steven Universe (RVCv2, RMVPE, And 300 Epochs/5400 Steps)

808s & Heartbreak Studio album by Kanye West All Songs I did on it Total Dataset Time 13:35 (Say You Will✅, Welcome To The Heartbreak❌ ,Heartless✅, Amazing❌ , Love Lockdown❌ Paranoid✅, Robocop✅, Street Lights✅, Bad News❌ See You In My Nightmares✅, Coldest Winter✅, Pinocchio Story❌❌❌) Reason Why I did it because the effects and also no one has done it yet. The pretrain is normal Epochs 375 36K Steps Batch Size 3

Kanye West (808s & Heartbreak Era)

The dataset is from the lossless audio of steven universe soundtrack.

Spinel Steven Universe (48K TITAN)

I put the batch size at 1 very low but try to make it accurate and I Find clean audios not from the show, and Music from the show but lossless ripped from Qobuz, Reason why because the tv show cutoff sample rate is 40K or even 32K. Also I use Titan 48K Pretrained

Peridot

Peridot (Talking And Singing 600 Epochs 54K Steps) 

Finally got around to making my first Kanye model somehow. Trained on 22 minutes of studio quality vocals from the Gallery sessions; pulled from the ye tracker. Despite being trained on mostly mumble, this model is great at singing. Very clean model with very little distortion. 40k Sample rate (dataset cutoff 19k) RVC v2 32 RMVPE hop length 8 Batch Size RIN_E3 pretrained Model

Kanye West

Kanye West (Donda v2 Gallery Sessions) (RMVPE, 850e, RIN-E3)

unitedshoes

version 25 of this mf model, i think this is the best it can get

Deep voice Playboi Carti

BABY BRUH

Future

Future - 2700 Steps

Future | We Dont Trust You Era

Future | We Dont Trust You Era | 300 Epochs

PlasmaTi

XXXTENTACION [Singing & Rapping]

XXXTENTACION [Singing & Rapping] UPDATED 550 Epochs (RVMPE 48K RVC V2)

I have a patreon where you can support my RVC stuff (colabs, guides, models, etc) and also get access to direct tech support on how to use the models Link to the 40khz version (I think I prefer this): Link to the 48khz version: Retrained with a better, crisper dataset courtesy of and trimmed down by hand, cleaned up, and further polished by me to the best 20 minutes of data that there is. I sent the dataset to nano so it could be trained by him on his fast AF GPU. Enjoy!

This dataset is mostly Yeezus 1 around 7 Min and 1 Min from Yeezus 2 So Around 9 Min, The Dataset I include this time is Blood On The Leaves Acapella leak., I know it's shorter than the other one, BUT this one sounded Better, less Noisy and It can handle Higher Pitch Range. I not include Cruel Summer Because Some of you wanted only 'Yeezus Stuff', The Pretrained Is Titan 48K 600 Epochs 52K STEPS!

Kanye West (Yeezus Era) Remake

Originally Trained on RVC (Text me on discord for any questions: pac.i) To use this model the best: Use clean audio with no noise, you can use several methods to remove the noise. You can use plugins like: RX-10 Denoise in your DAW Or You can use MVSEP.com and Denoise through AI As long as the audio is clean it doesn't matter If you want the BEST results possible download the model, and instead of using weights, run this through your own personal download of RVC on your computer.

Kanye West (Ultimate)

Paci

Made by me Google Drive THE PUBLIC NOW! New Policy - I will do your model if you pay up first. I will not do any samples anymore since people used me and wasted my time and blocked me. Thank you for understanding!  Doing commissions for personal models. Prices listed below, dm me for any questions or if interested! Also hit up if I'm fully booked!  Im also taking donations!

TY DOLLA $IGN

TY DOLLA $IGN RVC (1000 EPOCHS)

zafue

trained with a 6,5 minute dataset model other models:

Pusha T (Daytona Era Clean Vocals)

Description

Add a comment

Kanye West

Deep voice Playboi Carti

Future

Future | We Dont Trust You Era

XXXTENTACION [Singing & Rapping]

Kanye West

Kanye West (Yeezus Era) Remake

Kanye West (Ultimate)

TY DOLLA $IGN

Jadakiss

Saiba Momoi (Blue Archive)

Jungkook (BTS)

ENHYPEN Heeseung

Sas (Counter-strike global offensive)

Fang [Brawl Stars]

JENNIE of BLACKPINK [Strong Ver.]

Sunaokami Shiroko (Blue Archive)

Baldi (Baldi's Basics in Education and Learning)

Mortis [Brawl stars]

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

Sonic The Hedgehog [Roger Craig Smith]

JP Furina / Focalors CV: Inori Minase (Genshin Impact)

Surge (brawl Stars)

Janet (Brawl Stars)

Hu Tao JP (Genshin Impact)

Goku (Mario Castañeda) (Latin American Spanish) (UPDATE)

Villager (Minecraft)

FIXED HATSUNE MIKU V3 - VOCALOID [SCROLL DOWN FOR LINK]

Takanashi Hoshino (from Blue Archive)

Satoru Gojo (JJK) [VA Yuichi Nakamura]

Jay (ENHYPEN)

Tendou Arisu (Blue Archive)

Donald Trump

SpongeBob SquarePants (Talking And Singing)

Melodie - (Brawl Stars) - (English & Korean Voices)

Ariana Grande AI

CaseOh

Edgar [Brawl Stars]

Cordelius Brawl Stars

Alastor (Hazbin Hotel/English)