InspireFace is a cross-platform face recognition SDK developed in C/C++, supporting multiple operating systems and various backend types for inference, such as CPU, GPU, and NPU.

Easy to use device for connecting "old" measuring units (water, power, gas, ...) to the digital world

Training and using a neural network to read out the value of an analog display - example including small node server for demonstration

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

Use PEFT or Full-parameter to finetune 500+ LLMs (Qwen2.5, InternLM3, GLM4, Llama3.3, Mistral, Yi1.5, Baichuan2, DeepSeek-R1, ...) and 200+ MLLMs (Qwen2.5-VL, Qwen2-Audio, Llama3.2-Vision, Llava, I…

The Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems

https://hf.co/hexgrad/Kokoro-82M

AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:

RAG for Local LLM, chat with PDF/doc/txt files, ChatPDF. 纯原生实现RAG功能，基于本地LLM、embedding模型、reranker模型实现，无须安装任何第三方agent库。

DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

finetune-Qwen2-VL 2b/7b and LoRA

The reinforcement learning training code for AgiBot X1.

翻墙-科学上网、自由上网、免费科学上网、免费翻墙、油管youtube、fanqiang、软件、VPN、一键翻墙浏览器，vps一键搭建翻墙服务器脚本/教程，免费shadowsocks/ss/ssr/v2ray/goflyway账号/节点，翻墙梯子，电脑、手机、iOS、安卓、windows、Mac、Linux、路由器翻墙、科学上网、youtube视频下载、美区apple id共享账号

The project can achieve FCWS, LDWS, and LKAS functions solely using only visual sensors. using YOLOv5 / YOLOv5-lite / YOLOv6 / YOLOv7 / YOLOv8 / YOLOv9 / EfficientDet and Ultra-Fast-Lane-Detection-…

研究GOT-OCR-项目落地加速，不限语言

A Comprehensive Toolkit for High-Quality PDF Content Extraction

Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

[ECCV2024] API code for T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy

A one-stop, open-source, high-quality data extraction tool, supports PDF/webpage/e-book extraction.一站式开源高质量数据提取工具，支持PDF/网页/多格式电子书提取。

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.

EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine

real time face swap and one-click video deepfake with only a single image (uncensored)

A model that achieve dual detection(Infrared+RGB) with rotation

This project uses a variety of advanced voiceprint recognition models such as EcapaTdnn, ResNetSE, ERes2Net, CAM++, etc. It is not excluded that more models will be supported in the future. At the …

Quick exploration into fine tuning florence 2

[CVPR 2023] SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation

基于transformer的ocr识别，在公章(印章识别, seal recognition）拓展应用