Name: Derpy Hooves (My Little Pony Friendship is Magic) | AI RVC Model
Brand: Weights
Rating: 4.4 (23 reviews)

WebKit

 Introducing the Derpy Hooves Retrieval-Based Voice Conversion (RVC) Model version 2, trained for 200 epochs using the advanced Mangio-Crepe algorithm at Weights! Our state-of-the-art AI voice model captures the unique and beloved vocal characteristics of Derpy Hooves from My Little Pony Friendship is Magic, providing a natural and engaging user experience. Leveraging the power of RVC technology, we've developed an innovative system capable of converting speech, making it perfect for various applications such as creating AI covers or text-to-speech transformations.

Whether you're looking to generate realistic pony voices for your next animation project or simply want to explore the exciting world of AI music, our fine-tuned RVC Model offers unparalleled performance and versatility. With its improved accuracy and seamless integration into our cutting-edge platform, generating lifelike and entertaining audio has never been easier.

Discover the potential of artificial intelligence by trying out our free AI tools today! Simply visit weights.com and unlock endless creative possibilities with just a few clicks. Don't miss out – start crafting

Almost forgot to do this but I FINALLY retrained this model with Collab instead of kits, uses the same dataset as that model.

Derpy Hooves (My Little Pony Friendship is Magic)

Derpy Hooves (My Little Pony Friendship is Magic) - RVC v2, 200 Epochs, Mangio-Crepe

xhepyxopila

Tomas Dobell (AussieDingo)

personally I can't tell much of a difference

it doesn't really sound better to me but it *feels* better

you could use different inferring models on RVC in case it cracks on one part

Shamiko

x3meDerpy

The singer from those hilariously bad McDonalds Happy Meal ads from Pakistan. Trained off singing data from the Crash Bandicoot, Sonic, and Play Doh ads minus parts with backing vocals. 500 epochs, RMVPE, TITAN pretrain.

Pakistan McDonalds Ad Singer

Trained off voice lines from Wonder and NSMB U since they were the clearest quality. 300 Epochs, OV2 pretrain.

Kamek (Super Mario Franchise, Wii U / 3DS / Switch Era)

Trained off the uncompressed voice files for Star Fox 64 originally found in the 2020 Nintendo gigaleak. Model uses TITAN pretrain with 300 Epochs. Also I made a mistake and forgot to generate an index before training so uhh, I have no clue if doing it after training makes a difference.

Falco Lombardi (Star Fox)

Haven't tested yet but this should theoretically be my best Birdo model to date. Dataset used is Mario Kart 8 Deluxe BCP since it has her lines in the highest quality DeEcho'd and DeVerb'd so the results aren't weirdly robotic sounding RIN-E3 pretrain and 300 epochs.

Birdo (Super Mario Franchise) - The Final Model

Trained off 2 minutes of data with RIN-3 pretrain

Derpy Hooves (My Little Pony Friendship is Magic)

Description

Samples

Saiba Momoi (Blue Archive)

Adel imam (Egyptian Actor) عادل امام (ممثل مصري)

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

Ariana Grande AI

Hu Tao JP (Genshin Impact)

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)

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

Villager (Minecraft)

Mortis [Brawl stars]

Jungkook (BTS)

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

Tendou Arisu (Blue Archive)

Kanye West