Govo's repositories
Bert-VITS2
vits2 backbone with multilingual-bert
bisheng
Bisheng is an open LLM devops platform for next generation AI applications.
cron_next_rs
cron_next is a tool base on cron_clock and tokio, make it easy to use with cron jobs
chatbox
Chatbox is a desktop client for ChatGPT, Claude and other LLMs, available on Windows, Mac, Linux
ChatGPT-Next-Web
A cross-platform ChatGPT/Gemini UI (Web / PWA / Linux / Win / MacOS). 一键拥有你自己的跨平台 ChatGPT/Gemini 应用。
clarity-upscaler
Clarity AI | AI Image Upscaler & Enhancer - free and open-source Magnific Alternative
DeepFaceLive
Real-time face swap for PC streaming or video calls
ER-NeRF
[ICCV'23] Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis
GeneFace
GeneFace: Generalized and High-Fidelity 3D Talking Face Synthesis; ICLR 2023; Official code
google-signin-rs
Rust API bindings for Google Sign-in
GPT-SoVITS
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
kafka-node-async
Node.js client for Apache Kafka 0.8 and later.
LibreChat
Enhanced ChatGPT Clone: Features OpenAI, Assistants API, Azure, Groq, GPT-4 Vision, Mistral, Bing, Anthropic, OpenRouter, Vertex AI, Gemini, AI model switching, message search, langchain, DALL-E-3, ChatGPT Plugins, OpenAI Functions, Secure Multi-User System, Presets, completely open-source for self-hosting. More features in development
llama3
The official Meta Llama 3 GitHub site
MaxKB
💬 基于 LLM 大语言模型的知识库问答系统。开箱即用，支持快速嵌入到第三方业务系统，1Panel 官方出品。
mobc
A generic connection pool for Rust with async/await support
MuseV
MuseV: Infinite-length and High Fidelity Virtual Human Video Generation with Visual Conditioned Parallel Denoising
my_battery
检查安卓电量信息
nocobase
NocoBase is a scalability-first, open-source no-code/low-code platform for building business applications and enterprise solutions.
OpenDevin
🐚 OpenDevin: Code Less, Make More
Retrieval-based-Voice-Conversion-WebUI
Voice data <= 10 mins can also be used to train a good VC model!
Rope
GUI-focused roop
SadTalker-Video-Lip-Sync
本项目基于SadTalkers实现视频唇形合成的Wav2lip。通过以视频文件方式进行语音驱动生成唇形，设置面部区域可配置的增强方式进行合成唇形（人脸）区域画面增强，提高生成唇形的清晰度。使用DAIN 插帧的DL算法对生成视频进行补帧，补充帧间合成唇形的动作过渡，使合成的唇形更为流畅、真实以及自然。
screenshot-to-code
Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue)
so-vits-svc_fork
SoftVC VITS Singing Voice Conversion
unsloth
Finetune Llama 3, Mistral & Gemma LLMs 2-5x faster with 80% less memory
Wav2Lip-GFPGAN
High quality Lip sync
worker_threads_helper
worker_threads_helper