|国家预印本平台
首页|JoyTTS: LLM-based Spoken Chatbot With Voice Cloning

JoyTTS: LLM-based Spoken Chatbot With Voice Cloning

JoyTTS: LLM-based Spoken Chatbot With Voice Cloning

来源:Arxiv_logoArxiv
英文摘要

JoyTTS is an end-to-end spoken chatbot that combines large language models (LLM) with text-to-speech (TTS) technology, featuring voice cloning capabilities. This project is built upon the open-source MiniCPM-o and CosyVoice2 models and trained on 2000 hours of conversational data. We have also provided the complete training code to facilitate further development and optimization by the community. On the testing machine seed-tts-zh, it achieves a SS (speaker similarity) score of 0.73 and a WER (Word Error Rate) of 5.09. The code and models, along with training and inference scripts, are available at https://github.com/jdh-algo/JoyTTS.git.

Fangru Zhou、Jun Zhao、Guoxin Wang

计算技术、计算机技术

Fangru Zhou,Jun Zhao,Guoxin Wang.JoyTTS: LLM-based Spoken Chatbot With Voice Cloning[EB/OL].(2025-07-03)[2025-07-23].https://arxiv.org/abs/2507.02380.点此复制

评论