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.
☆53Updated 3 weeks 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:
- ☆197Updated 8 months ago
- Added vLLM support to IndexTTS for faster inference.☆171Updated last week
- flow mirror models from JZX AI Labs☆45Updated 8 months ago
- SenseVoice-python: A enterprise-grade open source multi-language asr system from funasr opensource with onnxruntime☆93Updated 8 months ago
- Extension of ChatTTS, 3x Faster on Windows, Support Voice Cloning and Mobile Deployment☆158Updated 3 months ago
- 基于FunASR实现语音识别,包含常规版和ONNX版(推荐)。☆39Updated 7 months ago
- A demo built on Megrez-3B-Instruct, integrating a web search tool to enhance the model's question-and-answer capabilities.☆38Updated 5 months ago
- ASR 2Pass onnxruntime and websocket server, based on FunASR(https://github.com/alibaba-damo-academy/FunASR).☆69Updated last month
- project page for ChatAnyone☆106Updated 2 months ago
- 文本语料转训练集工具,txt转dataset☆92Updated last year
- ☆230Updated 3 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 3 weeks ago
- Pseudo Streaming SenseVoice with Hotwords☆280Updated 2 months ago
- 简单实现VAD+声纹锁+SenseVoice完成类语音实时转录的小项目☆23Updated 8 months ago
- ☆377Updated 3 weeks ago
- Streaming ASR and TTS based on FastAPI+ sherpa-onnx☆114Updated last month
- F5-TTS 推理加速,速度提升约4倍!☆92Updated 4 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。☆54Updated 2 months ago
- 用于SenseVoice的api项目,输出带时间戳字幕☆34Updated 7 months ago
- Just a suturing monster project.☆41Updated last year
- A Simple MLLM Surpassed QwenVL-Max with OpenSource Data Only in 14B LLM.☆37Updated 8 months ago
- ☆55Updated 10 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☆387Updated 5 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆34Updated last week
- 我们是第一个完全可商用的角色大模型。☆40Updated 9 months ago
- GLM Series Edge Models☆139Updated 3 months ago
- 用于汇总目前的开源中文对话数据集☆159Updated 2 years ago
- 通过此代码可以免训练模型并通过轻量级服务器定制数字人形象☆103Updated last year
- RealSI: Open Benchmark for Simultaneous Interpretation in Real-world Scenarios☆53Updated 6 months ago
- The plan which extend ChatHaruhi into Zero-shot Roleplaying model☆106Updated last year