opendilab / CleanS2SLinks
High-quality and streaming Speech-to-Speech interactive agent in a single file. 只用一个文件实现的流式全双工语音交互原型智能体！
☆461Updated 3 months ago
Alternatives and similar repositories for CleanS2S
Users that are interested in CleanS2S are comparing it to the libraries listed below
Sorting:
- Stream-Omni is a GPT-4o-like language-vision-speech chatbot that simultaneously supports interaction across various modality combinations…☆343Updated 3 months ago
- PengChengStarling is specifically designed for developing multilingual ASR models based on the icefall project, supporting a complete ASR…☆181Updated 6 months ago
- ☆201Updated 11 months ago
- StyleLLM文风大模型：基于大语言模型的文本风格迁移项目。Text style transfer base on Large Language Model. #文字修饰 # 润色 #风格模仿☆320Updated last year
- Video QA Assistant based on LLMs with frame convolution☆212Updated last year
- StreamSpeech is an “All in One” seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.☆1,152Updated 2 months ago
- Graphrag的api扩展，可通过api调用，以嵌入在自己的web服务☆114Updated 9 months ago
- 通用大模型 × 文风大模型 = 多样化风格的聊天机器人☆49Updated last year
- ☆195Updated 9 months ago
- Multi-Agent-GPT: 一款基于RAG和agent构建的多模态专家助手GPT。它集成了文本、图像和音频等模态工具。支持本地部署和私有数据库建设。☆235Updated 7 months ago
- 使用vllm加速cosyvoice2的推理☆416Updated 4 months ago
- ✨✨Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM☆343Updated 3 months ago
- 基于Node.js、Vue3、uniapp的ChatGPT+智能体+Midjourney绘画+PPT生成+Suno音乐+Pika/Runway/Sora视频 网页服务 | 个人、团队、企业私有化AIGC平台☆261Updated 2 months ago
- Pseudo Streaming SenseVoice with Hotwords☆353Updated 6 months ago
- 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, …☆71Updated 4 months ago
- 本项目开源基于NextJS的前端， 希望能够提供一个用于生成式AI的文字转视频， 尤其是电影从编剧到视频生成的Web前端平台参考。Everyone can become a director. The Nextjs front-end of an AI driven pla…☆191Updated last year
- A LLM semantic caching system aiming to enhance user experience by reducing response time via cached query-result pairs.☆951Updated 2 months ago
- This is the code related to "🔥Effective Training Data Synthesis for Improving MLLM Chart Understanding" (ICCV 2025).☆54Updated last month
- A package for parsing PDFs and analyzing their content using LLMs.☆267Updated last year
- GPT-4o-level, real-time spoken dialogue system.☆355Updated 7 months ago
- Dolphin is a multilingual, multitask ASR model jointly trained by DataoceanAI and Tsinghua University.☆627Updated 2 months ago
- ☆121Updated 2 weeks ago
- Source code for ACL 2023 paper "End-to-End Simultaneous Speech Translation with Differentiable Segmentation"☆35Updated last year
- ☆112Updated last year
- MooER: Moore-threads Open Omni model for speech-to-speech intERaction. MooER-omni includes a series of end-to-end speech interaction mode…☆218Updated 8 months ago
- Paper list of simultaneous translation / streaming translation, including text-to-text machine translation and speech-to-text translation…☆583Updated last year
- EasyRAG是一个基于向量数据库的轻量级知识库检索系统，专为本地部署设计，对硬件要求极低。系统融合了现代数据治理理念，提供了友好的Web界面，支持多种文件格式的导入、分块和检索功能。该系统使用了检索增强生成（RAG）技术，可以有效地管理和检索大规模文档，同时确保数据的质量…☆115Updated 2 months ago
- 身份证OCR智能识别、证件提取以及验证码自动化解析功能,项目核心基于深度学习技术。从数据采集、数据标注 、模型训练、模型度量 、模型服务部署 全流程欢迎讨论。所有自训练模型、finetune欢迎自取使用，并持续关注我输出的更多模型。V:chenganp☆161Updated last month
- ☆451Updated 4 months ago
- A Template Based Report Rendering Platform.☆329Updated last year