asdfw13

GPT-SoVITS

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

so-vits-svc

SoftVC VITS Singing Voice Conversion

Retrieval-based-Voice-Conversion-WebUI

Easily train a good VC model with voice data <= 10 mins!

everyone-can-use-english

人人都能用英语

ultimatevocalremovergui

GUI for a Vocal Remover that uses Deep Neural Networks.

MediaCrawler

小红书笔记 | 评论爬虫、抖音视频 | 评论爬虫、快手视频 | 评论爬虫、B 站视频 ｜ 评论爬虫、微博帖子 ｜ 评论爬虫

llm-cookbook

面向开发者的 LLM 入门教程，吴恩达大模型系列课程中文版

Bert-VITS2

vits2 backbone with multilingual-bert

fish-speech

Brand new TTS solution

VirtualWife

VirtualWife是一个虚拟数字人项目，支持B站直播，支持openai、ollama

UwU

contentvec

speech self-supervised representations

CarpetSkyAdditions

Empty world generation with new ways to obtain resources

Diffusion-SVC

Music-Source-Separation-Training

Repository for training models for music source separation.

sr-message-maker

崩坏:星穹铁道风格短信的生成网站

NS2VC

Unofficial implementation of NaturalSpeech2 for Voice Conversion and Text to Speech

ar-vits

text to speech using autoregressive transformer and VITS

GenshinImpact_Start

FCPE

ReFlow-VAE-SVC

RMVPE

descript-audio-vae

VAE modified from Descript Audio Codec, which replaces the RVQ with VAE

Hifi-vaegan

keyclone

一个aardio语言写的键盘同步器，用于wow多开同步

glow-svc

glow-svc

singing voice conversion based on glow-tts

so-vits-svc

SoftVC VITS Singing Voice Conversion

so-vits-svc

SoftVC VITS Singing Voice Conversion

VST_NetProcess-

async http process VST plugin