Ninot1Quyi / Qwen2.5-Omni-multimodal-chatLinks
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, supporting real-time voice interaction, dynamic voice activity detection, and streaming audio processing.
☆55Updated last month
Alternatives and similar repositories for Qwen2.5-Omni-multimodal-chat
Users that are interested in Qwen2.5-Omni-multimodal-chat are comparing it to the libraries listed below
Sorting:
- ☆200Updated 8 months ago
- 基于FunASR实现语音识别，包含常规版和ONNX版(推荐)。☆39Updated 8 months ago
- Extension of ChatTTS, 3x Faster on Windows, Support Voice Cloning and Mobile Deployment☆163Updated 4 months ago
- ☆233Updated 4 months ago
- flow mirror models from JZX AI Labs☆44Updated 8 months ago
- GLM Series Edge Models☆142Updated last week
- GPT-4o-level, real-time spoken dialogue system.☆334Updated 4 months ago
- Added vLLM support to IndexTTS for faster inference.☆240Updated last week
- ☆145Updated last year
- A Multi-modal RAG Project with Dataset from Honor of Kings, one of the most popular smart phone games in China☆66Updated 9 months ago
- SenseVoice-python: A enterprise-grade open source multi-language asr system from funasr opensource with onnxruntime☆95Updated 8 months ago
- 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 3 weeks ago
- project page for ChatAnyone☆109Updated 2 months ago
- A demo built on Megrez-3B-Instruct, integrating a web search tool to enhance the model's question-and-answer capabilities.☆38Updated 6 months ago
- 我们是第一个完全可商用的角色大模型。☆40Updated 10 months ago
- 文本语料转训练集工具，txt转dataset☆92Updated last year
- 主要写er-nerf从零到一所有部署过程☆43Updated 9 months ago
- Bert-VITS2项目bug多且教程不友好。本proj尽可能修 复了Bert-vits2项目的bug，并且可一键启动训练。仅需50条目标说话人语音，获得稳定、快速的TTS模型。☆59Updated 3 months ago
- 实时STT，连接OpenAI接口/智谱AI（流式LLM）和GPT-SOVITS/Edge-TTS，通过网页的方式，进行跨网络的服务调用，实现实时对话的效果☆397Updated 5 months ago
- 使用langchain进行任务规划，构建子任务的会话场景资源，通过MCTS任务执行器，来让每个子任务通过在上下文中资源，通过自身反思探索来获取自身对问题的最优答案；这种方式依赖模型的对齐偏好，我们在每种偏好上设计了一个工程框架，来完成自我对不同答案的奖励进行采样策略☆29Updated last month
- 使用vllm加速cosyvoice2的推理☆340Updated last month
- Its an open source LLM based on MOE Structure.☆58Updated 11 months ago
- ☆161Updated 4 months ago
- Pseudo Streaming SenseVoice with Hotwords☆295Updated 3 months ago
- Real time faster whisper gradio☆26Updated 8 months ago
- 优化wav2lip的执行步骤，将头脸分离、嘴型替换、回补背景三个步骤分离，添加gfpgan强化面部功能，实现提前解帧，流式循环处理，对接obs☆73Updated 6 months ago
- 首个llama2 13b 中文版模型 （Base + 中文对话SFT，实现流畅多轮人机自然语言交互)☆90Updated last year
- ☆407Updated last month
- ☆56Updated 11 months ago
- A Simple MLLM Surpassed QwenVL-Max with OpenSource Data Only in 14B LLM.☆37Updated 9 months ago