vvsicdat

Results 3 comments of vvsicdat

> 合成音频时,文本分段后,每段的音频开始均会有滴的一声,听起来很奇怪,如下图,在切分后的每段文本开始前,总会有个明显的滴的一声噪音 ![image](https://github.com/user-attachments/assets/a32726de-3fa5-407b-814a-2b7f054f7852) > > [zero_shot_9222.wav.zip](https://github.com/user-attachments/files/17344112/zero_shot_9222.wav.zip) 我用的cosyvoice2-0.5B的模型也有这个问题,观察到音频开始时会有几十毫秒的杂音,不知是否时qihua大佬的vllm版本问题,求解决。

> > > > > 看看[https://github.com/qi-hua/async_cosyvoice的项目,VLLM能跑通](https://github.com/qi-hua/async_cosyvoice%E7%9A%84%E9%A1%B9%E7%9B%AE%EF%BC%8CVLLM%E8%83%BD%E8%B7%91%E9%80%9A)查看了 [https://github.com/qi-hua/async_cosyvoice 项,VLLMノ跑通](https://github.com/qi-hua/async_cosyvoice%E7%9A%84%E9%A1%B9%E7%9B%AE%EF%BC%8CVLLM%E8%83%BD%E8%B7%91%E9%80%9A) > > > > > > > > > > > > 这个试过啦,已经跑不通更新的模型了 > > > > > > > > >...