Official inference framework for 1-bit LLMs

Cool colorful backgrounds, generated by JS

so-vits-svc fork with realtime support, improved interface and more features.

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

A local chatbot fine-tuned by bilibili user comments.

A beautiful home server OS for self-hosting with an app store. Buy a pre-built Umbrel Home with umbrelOS, or install on a Raspberry Pi or any x86 system.

Fully open source, End to End Encrypted alternative to Google Photos and Apple Photos

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…

An Open Source text-to-speech system built by inverting Whisper.

AI Native Data App Development framework with AWEL(Agentic Workflow Expression Language) and Agents

OCR software, free and offline. 开源、免费的离线OCR软件。支持截屏/批量导入图片，PDF文档识别，排除水印/页眉页脚，扫描/生成二维码。内置多国语言库。

Code and models for NExT-GPT: Any-to-Any Multimodal Large Language Model

SoftVC VITS Singing Voice Conversion

A modern vue admin panel built with Vue3, Shadcn UI, Vite, TypeScript, and Monorepo. It's fast!

📮 A fully featured open source mail delivery platform for incoming & outgoing e-mail

Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

DELTA is a deep learning based natural language and speech processing platform.

Pronunciation lexicon covering both English and Chinese languages for Automatic Speech Recognition.

这是一个用C++实现ASR推理的项目，它依赖很少，安装也很简单，推理速度很快，在树莓派4B等ARM平台也可以流畅的运行。 支持的模型是由Google的Transformer模型中优化而来，数据集是开源wenetspeech(10000+小时)或阿里私有数据集(60000+小时)， 所以识别效果也很好，可以媲美许多商用的ASR软件。

FreeSWITCH is a Software Defined Telecom Stack enabling the digital transformation from proprietary telecom switches to a versatile software implementation that runs on any commodity hardware. From…

Graph Neural Network

MediaRecorder polyfill to record audio in Edge and Safari

🚀AI拟声: 5秒内克隆您的声音并生成任意语音内容 Clone a voice in 5 seconds to generate arbitrary speech in real-time

Spoken Language Identification on Common Voice and AudioSet using Deep Learning

Easy to use, state-of-the-art Neural Machine Translation for 100+ languages

Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and…

SeetaFace 2: open source, full stack face recognization toolkit.

SpaCy 中文模型 | Models for SpaCy that support Chinese