DanRuta / xVA-Synth

Machine learning based speech synthesis Electron app, with voices from specific characters from video games
GNU General Public License v3.0
590 stars 54 forks source link

How about translation other languages? #18

Open psycalc opened 3 years ago

psycalc commented 3 years ago

Guide plі in which (direction) neuron network (neural framework) you use and why? in wich direction should I look, in order too make voices more realistic, and sound in other languages? Is it possible at all or it is very complex and hard to train network?

psycalc commented 3 years ago

https://becominghuman.ai/generating-neural-speech-synthesis-voice-acting-using-xvasynth-fc978fdf24c1 sorry find myself

Pendrokar commented 1 year ago

v3 now supports multiple languages. A voice trained in English can somewhat also speak another language. Though more monotonally.

DanRuta commented 1 year ago

That article is super old. The v3 model now uses a slightly custom tweaked VITS/YourTTS model. Tweaks including larger capacity, bigger lang embedding, custom symbol set (a custom spec of ARPAbet with some more phonemes to cover other languages), and I guess a different training script.