S
StyleTTS2
yl4579/StyleTTS2
StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models
★6.3kstars
Python
MIT
Updated: Today
📋 Project at a Glance
Tap to expand
What's this?A adversarial-training/deep-learning tool in the Models category, built with Python, open-source
Who made it?Maintained by yl4579 team, 6.3K⭐ on GitHub, #239 out of 3201 in Models
Why does it exist?As the Models landscape evolved, the yl4579 team identified the need for better adversarial-training solutions. StyleTTS2 was created to simplify deep-learning workflows.
What can it do?Key use cases: diffusion-models, gan, latent-diffusion
How to install with AI?Use an AI coding assistant (Claude Code, Cursor, Copilot) to automatically set up pip dependencies and virtual env. Follow the README — the AI handles the rest.
🔗 github.com/yl4579/StyleTTS2
🔗 github.com/yl4579/StyleTTS2
Topics
adversarial-trainingdeep-learningdiffusion-modelsganlatent-diffusionlatent-diffusion-modelspytorchspeaker-adaptationspeech-synthesistext-to-speechttswavlm