rtll666 / realtime_vlm_systemLinks
A real-time swarf detection and analysis system based on YOLO and Qwen-vl-max, providing efficient video stream processing and intelligent analysis capabilities.
☆35Updated 2 months ago
Alternatives and similar repositories for realtime_vlm_system
Users that are interested in realtime_vlm_system are comparing it to the libraries listed below
Sorting:
- 一个基于多模态向量模型及视觉多模态模型构建的图片搜索引擎&管理系统，实现精准的以文搜文，文搜图、以图搜图多种智能检索方式。An image search engine management system built upon multimodal vector models…☆65Updated last month
- 小智的视觉对话☆30Updated 6 months ago
- ChatTTS HTTP API☆54Updated last year
- 使用FastAPI+vLLM部署Qwen2.5☆24Updated last year
- 小智机器人服务端☆18Updated 7 months ago
- 视频理解：千问视频多模态模型 & Dify☆65Updated last year
- In this fast-paced world, we all need a little something to spice up life. Whether you need a glass of sweet talk to lift your spirits or…☆59Updated 5 months ago
- This project provides a production-ready, real-time inference server for LatentSync, enabling high-quality, low-latency 2D digital human …☆18Updated 2 months ago
- ☆54Updated 7 months ago
- Sample GLM4V + ChatTTS AI assistant☆85Updated last year
- mcp的webui界面，支持客户端连接多 个sse服务端，支持 openai、deepseek、qwen等大模型，另外附上构建的 agent的 stdio和sse的简单 天气查询的完整示例☆36Updated 5 months ago
- Whisper realtime streaming for long speech-to-text transcription and translation☆57Updated last year
- This is a multi-character, ultra-personalized StoryTeller. It includes: 1) efficiently and accurately build multi-character voice library…☆55Updated 9 months ago
- 基于SenseVoice的funasr版本进行的api发布，可以无缝对接oneapi☆83Updated last year
- 💡💡💡awesome compute vision app in gradio☆55Updated last year
- 模型 llava-Qwen2-7B-Instruct-Chinese-CLIP 增强中文文字识别能力和表情包内涵识别能力，接近gpt4o、claude-3.5-sonnet的识别水平！☆25Updated last year
- 通过语音（说话）即可完成实时文本输入。通过PaddleSpeech项目二次开发 完成，支持离线脱网环境部署，支持GPU推理，目前客户端仅支持Windows。☆25Updated 2 years ago
- 文本语料转训练集工具，txt转dataset☆94Updated last year
- Built on the robust XTuner backend framework, XTuner Chat GUI offers a user-friendly platform for quick and efficient local model inferen…☆13Updated last year
- GOT-OCR的GUI版本，提供OCR、导出PDF、批处理等功能，但不提供训练功能☆182Updated 2 weeks ago
- An open-source chat text to control actions agentic workflow framework/showcase powered by Agently AI application development framework.☆29Updated last year
- Real-time video understanding and interaction through text,audio,image and video with large multi-modal model. 利用多模态大模型的实时视频理解和交互框架，通过文本…☆25Updated last year
- 基于youtube、bilibili等视频平台、webpage网页等，利用零一万物大模型或ollama本地小模型构建大语言模型高质量训练数据集（计划支持可自定义输出的训练数据格式）☆19Updated last year
- VideoFinder is an advanced video analysis tool powered by multimodal AI, designed to help users easily locate and identify specific objec…☆164Updated 11 months ago
- 🚀 轻量视频🎥 大模型🤖☆20Updated 6 months ago
- 万物检测（零样本检测+识别） demo for SG2300X 【Recognize Anything + GroundingDINO】☆23Updated last year
- ☆18Updated 6 months ago
- 一个面向多模态大模型训练的智能数据集构建与评估平台☆131Updated last month
- 研究GOT-OCR-项目落地加速，不限语言☆64Updated last year
- 基于通义千问 Qwen2.5-Omni 的实时语音对话系统，使用在线API服务，支持实时语音交互、动态语音活动检 测和流式音频处理。A real-time voice conversation system based on Qwen2.5-Omni Online-API, …☆78Updated 5 months ago