daniilrobnikov/vits2

VITS2: Improving Quality and Efficiency of Single-Stage Text-to-Speech with Adversarial Learning and Architecture Design

语言：Jupyter Notebook · GitHub 星标：648 · Fork：76

话题：deep-learning · pytorch · speech · speech-synthesis · text-to-speech · tts · vits2 · voice-conversion

在 GitHub 上查看原仓库