Name: Ein Audios | DMR V0.8 32K | AI RVC Model
Brand: Weights
Rating: 4.0 (1 reviews)

WebKit

Discover the Ein Audios | DMR V0.8 32K | Crepe 604 Epochs – an outstanding AI voice model designed by Weights. This model, meticulously refined over 604 epochs, is built on the innovative DMR V0.8 technology for high precision and superior quality. With a sample rate of 32k, the Ein Audios AI voice model renders impeccable voice modulation that serves as a perfect tool, especially for AI music and other audio applications. The model with its advanced batch size of 8 and hop length of 32 amplitude accuracy is capable of delivering excellent audio performance—a testament to its cutting-edge technology and rigorous design process. As a top-notch Retrieval-Based Voice Conversion (RVC) model, Ein Audios is explicitly created for producing remarkable AI covers with brilliant sound quality. Don't miss out on the opportunity to enhance your auditory experiences; utilize Weights' free AI tools today to experiment with the power of text-to-speech and the creativity behind AI covers!

This is a test of DMR V0.8. Info ish minutes - Sample Rate: 32k - Pretrain: DMR V0.8 - Batch Size: 8 - Hop Length: 32 Download

Ein Audios | DMR V0.8 32K

Ein Audios | DMR V0.8 32K | Crepe 604 Epochs

razeristaken

Troll model. Info Batch Size: 8 - Dataset Length: 20 min - Pretrain: Default - Sample Rate: 32k *Please credit me if used *

River | troll model

River | 130 Epochs | RMVPE | troll model

High pitched voice models are something. Info Batch Size: 8 - Dataset Length: 1 Hour - Pretrain: Default - Sample Rate: 32k *Please credit me if used *

Lazuli

Lazuli | 150 Epochs | RMVPE

Washed up e-girl turned Vtuber. Info Batch Size: 8 - Dataset Length: 1 Hour - Pretrain: Default - Sample Rate: 32k *Please credit me if used *

Kara Wilderwood

Kara Wilderwood | 198 Epochs | RMVPE

First male voice in how long? Probably to long. Info Batch Size: 8 - Dataset Length: 44 Minutes - Pretrain: Default - Sample Rate: 32k *Please credit me if used *

Alex O'Connor

Alex O'Connor | 244 Epochs | Rmvpe

So i tried out the Ranger optimizer with 5e-5 lr for the gen. Info Batch Size: 8 - Dataset Length: 50 Minutes - Pretrain: Default - Sample Rate: 32K *Please credit me if used *

Ein Audios | DMR V0.8 32K

Description

Samples

Emilia JP (Re:Zero)

Princess Daisy (Super Mario)

keri hilson "in a perfect world" era

frisk (undertale the musical)

cirno (chirumiru)

Jeff Lynne (Electric Light Orchestra)

Okuyasu Nijimura - JoJo - (JP Voice)

Mach-Hommy (pray for haiti)

Billie Eilish

Tamer

Kendrick Lamar (To Pimp a Butterfly Era)

Peter Knetter

Kagamine Len OG VA: Shimoda Asami (Project SEKAI)

Isaac Kleiner (Half-Life 2)

Valentine (Derpixon)

Isagi-Yoichi

Rusty Galloway (L.A. Noire)

Louane (FR)

Literally the Vowel Samples from SCRFilms' Audio Guide

Mammott (My Singing Monsters)

Nihmune Trained with 30min on clear audio

Hirohito, cleaner audio

Literally just a keyboard typing

Brown crewmate esculent (fnf: vs imposter v4)

- Johnny Depp - {Average Quality}

Walt Disney (Disney Founder) Low quality Audio 60s era

yes king Medium audio

Shizuku Hinomori (Project Sekai) - 320(?) Epochs

Catra - (32 Hop Length)

Kirisame Marisa (Touhou: Azure Reflections)

Einhar (Path of Exile)

Edward Robinson (Grant Wisler)

Albert Einstein

MrHoneyBun (Me, YouTuber) 64 Hop Length

Isabella Garcia-Shapiro (Phineas and Ferb)

Crash Woah Meme

Eric Clapton (SLOWHAND ERA)

CHRBRG / Charborg

Rainhoe 32k Sample

Nagisa Momoe (PMMM)

Koichi Hirose - JoJo - (JP Voice)

Shitno (fnf: hypno's lullaby.)

Alexander Graham Bell (Telephone Inventor) (1885 Era)

Erdem(Youtube audio dubbing content producer)

SalC1 (Ultra Quality Raw Audio Dataset)

Anny

Suletta Mercury (Mobile Suit Gundam The Witch From Mercury)

Mr. Potato Head - Toy Story

Pikachu

Eminem SSLP Era