Lists (5)
Stars
Long-form streaming TTS system for multi-speaker dialogue generation
A QEMU distro for Huawei's HarmonyOS Tablets and laptops, working in progress.
在鸿蒙上运行Linux Shell，支持手机、平板、2in1/PC、TV（Run Linux Shell on HarmonyOS, Phone/Pad/2in1/PC,TV are supported）
A terminal for running Linux ELF binary on HarmonyOS PC.
星河小程序 - 滴滴开源小程序 / Dimina MiniProgram - DiDi's Open-Source MiniProgram
⚡️鸿蒙Next Hap安装包合集，如果您觉得有帮助，还请点亮一下 Star 🌟 哦~ 万分感谢！
Termux for HarmonyOS Computer. Working in Progress.
RTMPose series (RTMPose, DWPose, RTMO, RTMW) without mmcv, mmpose, mmdet etc.
FlowGram is an extensible workflow development framework with built-in canvas, form, variable, and materials that helps developers build AI workflow platforms faster and simpler.
[CVPR 2025] Open-source, End-to-end, Vision-Language-Action model for GUI Agent & Computer Use.
Real Time (WebRTC & WebTransport) Proxy for LLM WebSocket APIs
A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription.
Box64 - Linux Userspace x86_64 Emulator with a twist, targeted at ARM64, RV64 and LoongArch Linux devices
first base model for full-duplex conversational audio
Android application for running Windows applications with Wine and Box86/Box64
Click-to-run debian 13 with desktop environment on android for Chinese users, with fcitx pinyin input method and some useful packages preinstalled. You don't need to install Termux.
It's a Virtual Machine App for Android Which is Based on QEMU
Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces
Inference code for the paper "Spirit-LM Interleaved Spoken and Written Language Model".
[CVPR 2024 Highlight] The official repo for "GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians"
Pseudo Streaming SenseVoice with Hotwords
Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"
Real time interactive streaming digital human
[CVPR 2024] This is the official source for our paper "SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis"