Giters

TimoBolkart / voca

This codebase demonstrates how to synthesize realistic 3D character animations given an arbitrary speech signal and a static character mesh.

Home Page:https://voca.is.tue.mpg.de/en

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

How do I use with python

007rohitSaini opened this issue · comments

commented

I want to make a chat bot with VOCA.
with python.
so how do I make it real-time and do I need to download 71 gb audio sequential for it.

commented

VOCA uses DeepSpeech as its backbone, which uses audio windows to generate 3D faces. This aggregates some past and future audio information to generate one frame. In this setting, it is not trivial to make it interactive. The implementation of the DeepSpeech as feature extractor also limits the execution time.