如果想在分离前先检测下是否存在语音混叠的情况,modelscope-funasr有办法或者有成熟模型可以用吗?
modelscope上有分角色识别模型和语音分离模型。https://modelscope.cn/models/iic/speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn/summary
https://modelscope.cn/models/iic/speech_mossformer2_separation_temporal_8k/summary
此回答整理自钉群“modelscope-funasr社区交流”