This repository give a guidline to learn CUDA and TensorRT from the beginning.

🚀 The fast, Pythonic way to build MCP servers and clients

"PhD-Level AI Agents: Fully-Automated Scientific Discovery with Our AI-Researcher Powered by LLMs"

Build your own AI friend

一个基于 WebRTC 和 Cloudflare Durable Objects 实现的简单高效的屏幕共享工具。通过 WebSocket 实现实时信令服务，配合 WebRTC 技术，实现低延迟的屏幕共享功能。只需输入投屏码，即可实现跨设备的屏幕分享。

Multilingual Voice Understanding Model

A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations

2018秋哈工大视听觉实验

J-Moshi: A Japanese Full-duplex Spoken Dialogue System

first base model for full-duplex conversational audio

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

On-device wake word detection powered by deep learning

A Lightweight Face Recognition and Facial Attribute Analysis (Age, Gender, Emotion and Race) Library for Python

Robust Speech Recognition via Large-Scale Weak Supervision

Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, Mistral Small 3.1 and other large language models.

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

WebRTC and ORTC implementation for Python using asyncio

Best practice TTS based on BERT and VITS with some Natural Speech Features Of Microsoft; Support ONNX streaming out!

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

[CVPR 2024] Real-Time Open-Vocabulary Object Detection

[ICCV 2023] Tracking Anything with Decoupled Video Segmentation

Export Segment Anything Models to ONNX

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

🔊 Text-Prompted Generative Audio Model

Light-weight system monitor for X, Wayland, and other things, too

[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

✯ 可直连访问的电视/广播图标库与相关工具项目 ✯ 🔕 永久免费 直连访问 完整开源 不断完善的台标 支持IPv4/IPv6双栈访问 🔕