How to upload/download pretrained voice-clone

FunAudioLLM / CosyVoice

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

https://funaudiollm.github.io/

Apache License 2.0

5.22k stars 535 forks source link

Open oovm opened 3 weeks ago

oovm commented 3 weeks ago

能不能和 gpt-sovits 一样根据多段对照文本生成声音, 然后生成缓存文件, 该文件可供下载

后续根据该声音特征文件, 重新合成声音

aluminumbox commented 2 weeks ago

well this is more like downstream task, you can write your own script, but this is not intended in this repo

oovm commented 2 weeks ago

可以说一下大概改哪里可以使用多个对照文本训练吗, 看起来只能用单个文本