A cute Shaoluo Yin with a good vocal range, Yoyo RVC model
Inference Comparison
After Inference
Other Inference
Model Introduction
It's been a while since I made this kind of model for everyone. I've been quite busy lately and still have other TTS orders on hand.
Last night, during some free time, I refined a little elixir for everyone. The cute Shao Luoyin was tested, and she could speak and sing without any issues (sound card test). The main reasoning was to set the pitch.
I set the tone to 14, which varies by person, but you can also follow the parameters I set below.

Here's a suggestion: the most common question people ask is, why do I use a different tone than yours! Here, I suggest that when you input the original voice, you can imitate speech. For example, if Youyou has a cute tone, then when you speak, you also need that cute tone to match the tone settings.
The sound range is good, and during testing, bass was also quite good.
Please note: I will place two pth modelsmygf-youyou_e180_s1980 and mygf-youyou. If you think the mygf-youyou file doesn't perform very well when using it, Then please use mygf-youyou_e180_s1980.
zhangzhang
Version Details
Recommended Parameters
Related Models
Keywords
Comments
No comments yet

