Ναρουσέ·μ·γιουμεμί·Χινακάννα's Projects
vits2 backbone with multilingual-bert
国产Galgame相关工具
Real-time end-to-end singing voice conversion system based on DDSP (Differentiable Digital Signal Processing)
Singing Voice Conversion via diffusion model
DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (SVS & TTS); AAAI 2022; Forked and maintained by the OpenVPI community
DiffSvcOnnx导出以及对MoeSS的适配
多个SVC/TTS的C++推理库
Mirror of https://git.ffmpeg.org/ffmpeg.git
An easy to understand TTS / SVS / SVC framework
使用傅里叶级数绘制任意图形
提取所有某些恶心人参与过的汉化项目文本
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
一个基于Mirai的功能性机器人
搬运自https://github.com/Anduin2017/HowToCook
使用MC之中的实体或者是信标播放一个黑白双色视频(微调程序可实现多种颜色)
使用Minecraft的粒子特效播放音乐
高效率 QQ 机器人支持库
Config files for my GitHub profile.
ncnn is a high-performance neural network inference framework optimized for the mobile platform
OpenGL Mathematics (GLM)
PITS: Variational Pitch Inference for End-to-end Pitch-controllable TTS without External Pitch Predictor
RequireMent Model For MoeSS
Easily train a good VC model with voice data <= 10 mins!
一个基于mirai,针对粉丝群管理的插件
一个集成了各种有趣和实用AI项目的工具箱
SoftVC VITS Singing Voice Conversion