Dolphin is a multilingual, multitask ASR model jointly trained by DataoceanAI and Tsinghua University.

一款提示词优化器，助力于编写高质量的提示词

这是一个简单的技术科普教程项目，主要聚焦于解释一些有趣的，前沿的技术概念和原理。每篇文章都力求在 5 分钟内阅读完成。

Xiaozhi MCP sample program

虾哥的小智 AI 聊天机器人（XiaoZhi AI Chatbot）- python客户端

A high-quality tool for convert PDF to Markdown and JSON.一站式开源高质量数据提取工具，将PDF转换成Markdown和JSON格式。

A Repository for Single- and Multi-modal Speaker Verification, Speaker Recognition and Speaker Diarization

本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.

COLMAP - Structure-from-Motion and Multi-View Stereo

Open3D: A Modern Library for 3D Data Processing

The open source mesh processing system

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

python版本的小智ai，主要帮助那些没有硬件却想体验小智功能的人

Silero VAD: pre-trained enterprise-grade Voice Activity Detector

Build your own AI friend

The ESP-BOX is a new generation AIoT development platform released by Espressif Systems.

AigcPanel 是一个简单易用的一站式AI数字人系统，支持视频合成、声音合成、声音克隆，简化本地模型管理、一键导入和使用AI模型。

Qwen2.5-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

Visual-SLAM based on COLMAP API

Unofficial revival of the well known .NET debugger and assembly editor, dnSpy

Use Microsoft Edge's online text-to-speech service from Python WITHOUT needing Microsoft Edge or Windows or an API key

Build your own AI friend

Point-LIO algorithm for Unitree LiDAR products.

一个 PC 桌面聊天助手，试试把 LLM 跟 IM 结合。

对ESP32CAM的二维码识别

Trained models with fast variant of the "best" LSTM models + legacy models

快速將 PDF 轉換為 Markdown，精度高。現階段中文應該不行。Convert PDF to markdown quickly with high accuracy

MATLAB MAT File I/O Library

A Modbus library for Linux, Mac OS X, FreeBSD, QNX and Windows

Xilinx QDMA IP Drivers