Xiaorui girly voice, ridiculous, RVC model

Xiaorui is a carefully designed large model that includes a one-hour raw dataset, including chatting, singing, treble, and bass. In testing, the model's support for laughter is quite good. Below, I will list the results after multiple inference audio tests, including the smile aspect that everyone cares about most.

Laughter

<!--[if lt IE 9]>document.createElement('audio');<![endif]-->

Speak plainly

Male to female

Parameters

Audio analysis