henttttai / voice-to-voice-llm-structureLinks
自用，语音到文本用的sencevoice，llm部分基于ollama的API调用，文本到语音用的cosyvoice，实时语音输入参考的https://github.com/ABexit/ASR-LLM-TTS。
☆11Updated last year
Alternatives and similar repositories for voice-to-voice-llm-structure
Users that are interested in voice-to-voice-llm-structure are comparing it to the libraries listed below
Sorting:
- 简单实现VAD+声纹锁+SenseVoice完成类语音实时转录的小项目☆42Updated last year
- 一个模块化，全过程可离线，低占用率的对话机器人/智能音箱☆124Updated last week
- Utilizes ONNX Runtime for speech activity detection.☆38Updated 2 weeks ago
- 端到端语音唤醒工具箱，从模型训练到模型推理。☆147Updated 4 months ago
- ASR 2Pass onnxruntime and websocket server, based on FunASR(https://github.com/alibaba-damo-academy/FunASR).☆93Updated last month
- SenseVoice-python: A enterprise-grade open source multi-language asr system from funasr opensource with onnxruntime☆108Updated 2 months ago
- funasr语音转文字的简单api版本，funasr+fastapi，方便部署在服务器上☆13Updated last year
- 开源语音识别自定义数据模型训练指南☆12Updated 2 years ago
- CosyVoice语音合成简易API☆13Updated last year
- SummerAsr 是一个基于C++的可独立编译且几乎没有额外依赖库的本地中文语音识别器。 Summer Asr is a Chinese automatic speech recognize project written with C++ that can be eas…☆99Updated last year
- some ncnn demos of FunASR☆28Updated last year
- Utilizes ONNX Runtime to transcribe audio into text.☆63Updated last week
- 基于FunASR实现语音识别，包含常规版和ONNX版(推荐)。☆46Updated last year
- 语音识别模型pytorch转ONNX转MNN，C++实现部署☆82Updated 3 years ago
- Pseudo Streaming SenseVoice with Hotwords☆409Updated 9 months ago
- 基于ONNXRuntime以及LLama.cpp推理引擎实现的高性能C++语音推理框架，在性能极差的边缘设备上都能做到RTF<0.7实时对话。☆31Updated this week
- A enterprise-grade Voice Activity Detector from modelscope and funasr.☆120Updated 2 years ago
- A cross platform implementation of Text-to-Speech based on ONNXRuntime.☆33Updated 2 years ago
- ChatTTS HTTP API☆54Updated last year
- Streaming ASR and TTS based on FastAPI+ sherpa-onnx☆177Updated last month
- Port of Funasr's Paraformer model in C/C++☆39Updated last year
- 用于SenseVoice的api项目，输出带时间戳字幕☆43Updated last year
- ☆69Updated last year
- ☆204Updated last year
- Fun-ASR is an end-to-end speech recognition large model launched by Tongyi Lab.☆503Updated this week
- 本地完整部署ASR(K2)-NLP(Rasa,Spacy)-LLM(Chatglm2)-TTS(Vits)☆150Updated 8 months ago
- 使用onnxruntime部署实时视频帧插值，包含C++和Python两个版本的程序☆27Updated last year
- 阿里SenseVoice的fastpi封装，采用onnx发布，体积更小，附带量化模型，支持GPU。支持从URL文件进行语音识别。☆104Updated last year
- paraformer(chinense asr) online onnx runtime for python☆53Updated last year
- DH-Live-Web-UI☆19Updated last year