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.
☆60Updated 2 months ago
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:
- ☆201Updated 10 months ago
- Extension of ChatTTS, 3x Faster on Windows, Support Voice Cloning and Mobile Deployment☆169Updated 5 months ago
- 基于FunASR实现语音识别，包含常规版和ONNX版(推荐)。☆41Updated 9 months ago
- SenseVoice-python: A enterprise-grade open source multi-language asr system from funasr opensource with onnxruntime☆97Updated 10 months ago
- ☆429Updated 2 months ago
- Added vLLM support to IndexTTS for faster inference.☆348Updated 2 weeks ago
- ☆235Updated 5 months ago
- flow mirror models from JZX AI Labs☆44Updated 10 months ago
- GPT-4o-level, real-time spoken dialogue system.☆348Updated 6 months ago
- Pseudo Streaming SenseVoice with Hotwords☆319Updated 4 months ago
- The plan which extend ChatHaruhi into Zero-shot Roleplaying model☆108Updated last year
- ☆364Updated last year
- 第一个支持中英文双语语音-文本多模态对话的开源可商用对话模型。便捷的语音输入将大幅改善以文本为输入的大模型的使用体验，同时避免了基于 ASR 解决方案的繁琐流程以及可能引入的错误。☆556Updated last year
- 简单实现VAD+声纹锁+SenseVoice完成类语音实时转录的小项目☆31Updated 10 months ago
- 文本语料转训练集工具，txt转dataset☆93Updated last year
- 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 3 weeks ago
- ☆151Updated last year
- Dynamic Voice Actor Assignment and Emotional Narration for Realistic Story Play☆39Updated 3 months ago
- 用于汇总目前的开源中文对话数据集☆168Updated 2 years ago
- An open source chat bot architecture for voice/vision (and multimodal) assistants, local(CPU/GPU bound) and remote(I/O bound) to run.☆64Updated this week
- 使用甄嬛语料微调的chatglm☆86Updated 2 years ago
- 使用vllm加速cosyvoice2的推理☆375Updated 3 months ago
- MOSS-TTSD is a spoken dialogue generation model that enables expressive dialogue speech synthesis in both Chinese and English, supporting…☆637Updated this week
- Just for debug☆56Updated last year
- RealSI: Open Benchmark for Simultaneous Interpretation in Real-world Scenarios☆61Updated 3 weeks 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☆405Updated 7 months ago
- Dolphin is a multilingual, multitask ASR model jointly trained by DataoceanAI and Tsinghua University.☆579Updated 2 weeks ago
- ☆59Updated last year
- This is a multi-character, ultra-personalized StoryTeller. It includes: 1) efficiently and accurately build multi-character voice library…☆46Updated 5 months ago
- Its an open source LLM based on MOE Structure.☆58Updated last year