HeyangXue1997

GradTTS. Pytorch implementation of "Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech"

Learn2Sing2.0. Diffusion and Mutual Information-Based Target Speaker SVS by Learning from Singing Teacher

WaveODE. An ODE-based generative neural vocoder using Rectified Flow

EMPHASIS-pytorch. EMPHASIS: An Emotional Phoneme-based Acoustic Model for Speech Synthesis System

Zoneout-Pytorch. A zoneout implemetion based on pytorch

Tacotron2-pytorch. Tacotron2 implemented by pytorch

MoE-TTS. HTML

multi-gradspeech. JavaScript

noise_robust_svs. HTML