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
711 stars 87 forks source link

[Feature] Improve streaming results #70

Closed zhzLuke96 closed 3 months ago

zhzLuke96 commented 3 months ago

功能描述

相关 #5

问题

stream api 已实现，但是有未知原因导致生成结果不理想有杂音

tts 生成: https://github.com/lenML/ChatTTS-Forge/assets/37396659/ac961b7b-dbd9-4f81-a106-a486051e45a5

流式生成: https://github.com/lenML/ChatTTS-Forge/assets/37396659/a602e813-7059-474a-a603-86fd9ab6af05

todo list

可能的解决方案

可能需要依赖上游代码库修复

zhzLuke96 commented 3 months ago

fixed

NOTE: ssml 还不支持流式输出