search

FunAudioLLM / CosyVoice

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
https://funaudiollm.github.io/
Apache License 2.0
2.52k stars 230 forks source link

speaker #38

Closed Lixi20 closed 1 week ago

Lixi20 commented 2 weeks ago

可以识别音频里面的speaker吗。有没有借口？

Lixi20 commented 2 weeks ago

可以识别音频里面的speaker吗。有没有接口？

ZhihaoDU commented 1 week ago

我想你要找的是SenseVoice或者3D-speaker。CosyVoice是生成模型，不能识别说话人。