Results 3 comments of zhuchen

> 出来的音频要选raw格式,不要用wav格式。 另外采样率是32khz吗 感谢回复, 出来的是wav+24khz,不是raw+32khz。 我在ttsreal.py代码里修改了采样率,音色是对的,这个嗒声是因为不是raw格式的问题吗?咱代码里有办法优化吗? ![image](https://github.com/user-attachments/assets/befb3ae5-925a-4a4d-8bad-f4c39097e827)

> 要去掉wav头 44byte 感谢, 我这么去掉后,开头没嗒声了, 但内部会有几次小声的噪音, 是我去的不对吗? ![image](https://github.com/user-attachments/assets/0d3969a4-038c-4190-82e5-e04424c6dc4a)

> Could you try my version, I switched to a different pkuseg and it appears to work good (test multilingual model with Chinese text) > > https://github.com/rsxdalv/chatterbox/tree/faster success