A girly voice RVC model with excellent Cantonese support

Actually, the RVC project isn't very language-specific, but for example, some anime models in Miaoyin, especially Japanese models, when you do reasoning, if the original dataset isn't trained in Chinese, the results will have a strong JP sound. This is also why some model authors train a separate language.

This model is specially trained for those who are accustomed to using "Cantonese," and all the training data is in Cantonese, so it has excellent support for Cantonese.

The dataset is composed by fusing multiple Cantonese voice colors, and switching tones during use may produce mature accents and similar effects.

No reasoning has been

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

After reasoning

Singing performance

parameters

training log