Install Steam
login
|
language
简体中文 (Simplified Chinese)
繁體中文 (Traditional Chinese)
日本語 (Japanese)
한국어 (Korean)
ไทย (Thai)
Български (Bulgarian)
Čeština (Czech)
Dansk (Danish)
Deutsch (German)
Español - España (Spanish - Spain)
Español - Latinoamérica (Spanish - Latin America)
Ελληνικά (Greek)
Français (French)
Italiano (Italian)
Bahasa Indonesia (Indonesian)
Magyar (Hungarian)
Nederlands (Dutch)
Norsk (Norwegian)
Polski (Polish)
Português (Portuguese - Portugal)
Português - Brasil (Portuguese - Brazil)
Română (Romanian)
Русский (Russian)
Suomi (Finnish)
Svenska (Swedish)
Türkçe (Turkish)
Tiếng Việt (Vietnamese)
Українська (Ukrainian)
Report a translation problem
learn this sh*t:
https://steamcommunity.com/sharedfiles/filedetails/?id=2976976206
and then figure this crap out:
https://github.com/SayaSS/vits-finetuning
Thanks for your kindness guy
isn't so-vits purely a SVC model, i really couldn't see TTS working with it
well if you want the transcriptions, i suggest getting the subtitle vdfs, you could get them by extracting them from the game's main pak data ( pak01_dir.vpk ).
they are located in the resource folder and they are usually named something like subtitles_japanese.txt
but don't be deceived as they are not simple .txt files but valve data formats, which is really a hassle to work with on itself, you would need to convert it into json.
but luckily guitargamer made a python script for that, i can give it to you if you are still interested.
@Jo Please make Daiyousei for Nick.
Limitations of the model really, its not exactly voice cloning tech as you would hear in Elevenlabs, This is just text to speech synthesis.