Whats this?
This is model for so-vits fork.
English Description.
Model Speaker: Nao Toyama
Main Anime: My Youth Romantic Comedy Is Wrong As I Expected English, titles of Rascal series, A Couple of Cuckoos, Laid-Back Camp, Rent A Girlfriend, Classroom of the Elite, Nisekoi: False Love
Memo; This model was trained up to 30000 epoch by Paperspace's RTX-A4000.
It may not be able to produce high pitched voices, etc.
If you would like to hear a sample of the voice, please watch the video below.
説明(Japanese Description.)
このボイスデータのモデル: 東山 奈央(とおやま なお)
主な出演アニメ: 俺ガイル, 青春ブタ野郎シリーズ, カッコウの許嫁, ゆるキャン△, 彼女お借りします, よう実, ニセコイ
メモ:このモデルはPaperspaceのRTX-A4000で30000エポックまで学習させたモデルです。
高い声などは上手く出せないかもしれません。
声を試しに聞きたい方は、以下のビデオを見てください。
Description
Ver.1.1
Fix ReadMe file
Add launch.bat
FAQ
Comments (2)
There is only one cluster file and 3 pth models..
How come you can create 5 different voice characters?
do you have any settings to share? I am using voice changer Client from https://github.com/w-okada/voice-changer
Do you recommend other GUI?
It seems like there is something wrong with the config file you provided, at least the ssl_dim is not consistent with the pth file. Even after I correct the config file, I can only generate strange sound from this model.
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.