search

lenML / Speech-AI-Forge

🍦 Speech-AI-Forge is a project developed around TTS generation model, implementing an API Server and a Gradio-based WebUI.
https://huggingface.co/spaces/lenML/ChatTTS-Forge
GNU Affero General Public License v3.0
710 stars 87 forks source link

[Plan] support ChatTTS zero shot infer #113

Closed zhzLuke96 closed 2 months ago

zhzLuke96 commented 2 months ago

实现导入脚本，以支持将克隆音色导入 forge 中 ref: https://github.com/2noise/ChatTTS/issues/369

TODOs

IrisSally commented 2 months ago

2noise-ChatTTS官方已开源Open-source DVAE encoder and zero shot inferring code.

https://github.com/2noise/ChatTTS/commit/6f4ceb9d46b1155ac9368a3be06c7917710e55e9

IrisSally commented 2 months ago

image

zhzLuke96 commented 2 months ago

added https://github.com/lenML/ChatTTS-Forge/commit/ff4991e0131ab38a929815dedbfbaf1e5b8f854a

相关讨论 https://github.com/lenML/ChatTTS-Forge/discussions/118