Introducing the Shrek v2 [English/Retrained] (RVC v2) [500 Epochs/7.5k Steps], a retrained version of the classic Shrek voice lines by Mike Myers using the RVC v2 model. This new iteration has been normalized, meaning all voice lines have been evenly adjusted to be louder than before. Despite being trained with a larger number of epochs and remaining in the iconic Scottish dialect, the voice retains its original distinctiveness. The model uses a Mangio-Crepe algorithm, with a hop length of 64 and a target sample batch size of 20. Get started creating your own AI covers and text-to-speech today with our powerful and easy-to-use free AI tools.

with the same dataset of 8 minutes and 17 seconds but normalized (normalized means all his voice lines should be equally louder compared to the old one) Voiced by Mike Myers Mangio-Crepe/64 Hop-Length 40k Target Sample Batch Size 20 Even though all his voice lines are in Scottish dialect and trained with larger number of epochs, his dialect is still non-existent

Shrek [English/Retrained]

Shrek v2 [English/Retrained] (RVC v2) [500 Epochs/7.5k Steps]

SyberG

🔗Link: https://huggingface.co/SyberGen/Shrek-VModels/resolve/main/Shrek-v2.zip
🚆Trained with the same dataset of 8 minutes and 17 seconds but normalized (normalized means all his voice lines should be equally louder compared to the old one)
🎙️Voiced by Mike Myers

🔊Mangio-Crepe/64 Hop-Length
🎯40k Target Sample
💼Batch Size 20

💀Even though all his voice lines are in Scottish dialect and trained with larger number of epochs, his dialect is still non-existent💀

thedoodooman

freshalicious

250 Epochs > Trained with 8 minutes and 54 seconds of dataset > Pretrained with TITAN > Vocals Isolated + Noise Removed > Voiced by Ai Nonaka > 5.5k Steps > RVMPE/64 Hop-Length > 40k Target Sample > Batch Size 8

Madobe Touko [2019-2020 Graduation Era | Digital DIY]

Madobe Touko [2019-2020 Graduation Era | Digital DIY] (RVC v2 | 250 Epochs)

250 Epochs > Trained with 7 minutes and 15 seconds of dataset > Pretrained with TITAN > Vocals Isolated + Noise Removed > Voiced by Nana Mizuki > 5k Steps > RVMPE/64 Hop-Length > 40k Target Sample > Batch Size 8 > Just found out that she actually graduated in Jan 2020 (a.k.a Win 7's end of support)

Madobe Nanami [2019-2020 Graduation Era | Digital DIY]

Madobe Nanami [2019-2020 Graduation Era | Digital DIY] (RVC v2 | 250 Epochs)

100 Epochs > Trained with 45 minutes and 29 seconds of dataset > Pretrained with TITAN > Normalized + Echo and Noise Removed > Voiced by Ry Horikawa > 10.6k Steps > RVMPE/64 Hop-Length > 40k Target Sample > Batch Size 8

Vegeta [DB-FighterZ | 🇯🇵] [All Transformations Combined]

Vegeta [DB-FighterZ | 🇯🇵] [All Transformations Combined] (RVC v2 | 100 Epochs)

100 Epochs > Trained with 37 minutes and 5 seconds of dataset > Pretrained with TITAN > Normalized + Echo and Noise Removed > Voiced by Masako Nozawa > 9k Steps > RVMPE/64 Hop-Length > 40k Target Sample > Batch Size 8

Son Goku [DB-FighterZ | 🇯🇵] [All Transformations Combined]

Son Goku [DB-FighterZ | 🇯🇵]  [All Transformations Combined] (RVC v2 | 100 Epochs)

500 Epochs > Trained with 42 seconds of dataset > Pretrained with TITAN > Vocals Isolated + Noise Removed > Voiced by Christian Bernard > 2k Steps > RVMPE/64 Hop-Length > 40k Target Sample > Batch Size 8

Glass Joe [Punch-Out!! Wii]

Bubbles (The Powerpuff Girls) (Tara Strong)

Bubbles (The Powerpuff Girls) (Tara Strong) (250 Epochs) (RVC V2)

A Living Gift

This model was trained on the few Clancy Brown video game voice lines I could find. In total it is roughly around 10 minutes or so of audio. It was trained using the crepe method on RVC. Should work well with vocal impressions and possibly singing, but has yet to be tested. Hugging Face Mirror:

Mr. Krabs (SpongeBob)

Mr. Krabs (SpongeBob) RVC 1.25K Epochs [56.25K Steps]

ell0er

The Minions

The Minions (RVC V2) (390 EPOCHS)

My most ridiculous model yet. Dataset was 1:00 (8.6 seconds repeated). Hurt noises were included, so you will hear hitting noises often.

Villager (From Minecraft)

Villager (From Minecraft) (RVC v2) 500 Epoch

analogspiderweb

Alright yes I know there's already several Toad models posted in the server. But none of them took advantage of the fact that we have 20 years of Toad screaming. Credit to the guys over on the VG Resource for ripping Toad's voice clips from nearly every Mario game. Dataset totals to 16 minutes. All the voice clips are direct rips from 10+ different Mario games. I recommend setting the pitch to +12 and above. Enjoy.

Toad - Super Mario

Toad - Super Mario (RVC v2) (400 epoch)

Big Mitch

(Mangio-Crepe): v1 (Crepe): "DOOOOOOOOOOOOOODGE!!"

Piccolo (DBZ)

Piccolo (DBZ) (RVC v2) (Mangio-Crepe/Crepe) - 300 Epochs

Model: < Search feature ratio = 0.9 for best results! Sample Rate: 48k Epochs: 120 10 minute dataset from Despicable Me on PS2, Trained with RMVPE Overtrained very quickly for some reason

Gru (Despicable Me)

Gru (Despicable Me) (RVC v2) (120 Epochs)

hello here is my Michael Jackson model for RVC this model was specifically trained with his Harsh vocals <

Michael Jackson

Michael Jackson RVC (1000 Epoch)

Voice clips sourced from the PS2 version of the Toy Story 3 video game. Credit me if used!

Jessie (Toy Story series)

Jessie (Toy Story series) (RVC v2, RMVPE) (200 epochs)

ShiverThermal

If you going to use them, go ahead. But uh... just don't credit me, okay? I don't want to get in trouble for this! Just put me under the name "UnknownBandit"

Shrek [English/Retrained]

Description

Add a comment

Bubbles (The Powerpuff Girls) (Tara Strong)

Mr. Krabs (SpongeBob)

The Minions

Villager (From Minecraft)

Toad - Super Mario

Piccolo (DBZ)

Gru (Despicable Me)

Michael Jackson

Jessie (Toy Story series)

Star Butterfly (Star Vs the Forces of Evil)

Saiba Momoi (Blue Archive)

Jungkook (BTS)

Sonic The Hedgehog [Roger Craig Smith]

ENHYPEN Heeseung

CaseOh

Villager (Minecraft)

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

Ariana Grande AI

Satoru Gojo (JJK) [VA Yuichi Nakamura]

Fang [Brawl Stars]

Mortis [Brawl stars]

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

Takanashi Hoshino (from Blue Archive)

Sas (Counter-strike global offensive)

Edgar [Brawl Stars]

SpongeBob SquarePants (Talking And Singing)

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

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

Surge (brawl Stars)

JENNIE of BLACKPINK [Strong Ver.]