k2-fsa / sherpa-ncnnLinks
Real-time speech recognition and voice activity detection (VAD) using next-gen Kaldi with ncnn without Internet connection. Support iOS, Android, Linux, macOS, Windows, Raspberry Pi, VisionFive2, LicheePi4A etc.
☆1,483Updated this week
Alternatives and similar repositories for sherpa-ncnn
Users that are interested in sherpa-ncnn are comparing it to the libraries listed below
Sorting:
- Speech-to-text server framework with next-gen Kaldi☆774Updated this week
- SummerTTS 是一个基于C++的独立编译的中文和英文语音合成项目,可以本地运行不需要网络,而且没有额外的依赖,一键编译完成即可用于中文和英文的语音合成。SummerTTS is a standalone Chinese and English speech synt…☆494Updated 2 months ago
- Port of Funasr's Sense-voice model in C/C++☆437Updated 2 months ago
- 这是一个用C++实现ASR推理的项目,它依赖很少,安装也很简单,推理速度很快,在树莓派4B等ARM平台也可以流畅的运行。 支持的模型是由Google的Transformer模型中优化而来,数据集是开源wenetspeech(10000+小时)或阿里私有数据集(60000+小…☆539Updated 2 years ago
- Production First and Production Ready End-to-End Keyword Spotting Toolkit☆617Updated this week
- 📣 商用级开源语音自动识别程序库,开箱即用,全平台支持,中英文混合识别。A Cross-platform implementation of ASR inference. It's based on ONNXRuntime and FunASR. We provide …☆582Updated last year
- Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training wit…☆1,122Updated 3 months ago
- Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime…☆7,394Updated this week
- funasr-android 本地化部署 生成.so给安卓那边调用☆44Updated 5 months ago
- ☆1,231Updated last week
- A Repository for Single- and Multi-modal Speaker Verification, Speaker Recognition and Speaker Diarization☆2,395Updated last month
- Best practice TTS based on BERT and VITS with some Natural Speech Features Of Microsoft; Support ONNX streaming out!☆1,211Updated last year
- Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR be…☆1,352Updated 5 months ago
- Pseudo Streaming SenseVoice with Hotwords☆349Updated 6 months ago
- Production First and Production Ready End-to-End Speech Recognition Toolkit☆4,800Updated last week
- 基于PaddlePaddle实现端到端中文语音识别,从入门到实战,超简单的入门案例,超实用的企业项目。支持当前最流行的DeepSpeech2、Conformer、Squeezeformer模型☆864Updated 3 months ago
- This project uses a variety of advanced voiceprint recognition models such as EcapaTdnn, ResNetSE, ERes2Net, CAM++, etc. It is not exclud…☆1,108Updated 3 months ago
- FSA/FST algorithms, differentiable, with PyTorch compatibility.☆1,260Updated last month
- Pytorch实现的流式与非流式的自动语音识别框架,同时兼容在线和离线识别,目前支持Conformer、Squeezeformer、DeepSpeech2模型,支持多种数据增强方法。☆702Updated 3 months ago
- API and websocket server for sensevoice. It has inherited some enhanced features, such as VAD detection, real-time streaming recognition,…☆504Updated 10 months ago
- KAN-TTS is a speech-synthesis training framework, please try the demos we have posted at https://modelscope.cn/models?page=1&tasks=text-…☆521Updated last year
- Android Voice Activity Detection (VAD) library. Supports WebRTC VAD GMM, Silero VAD DNN, Yamnet VAD DNN models.☆408Updated 2 months ago
- 百聆 是一个类似GPT-4o的语音对话机器人,通过ASR+LLM+TTS实现,集成DeepSeek R1等优秀大模型,时延低至800ms,Mac等低配置也可运行,支持打断☆1,436Updated last month
- Research and Production Oriented Speaker Verification, Recognition and Diarization Toolkit☆1,027Updated last week
- Web interface for creating snowboy personal wake words locally☆146Updated last year
- 使用vllm加速cosyvoice2的推理☆416Updated 4 months ago
- ☆764Updated last year
- Multilingual Voice Understanding Model☆6,598Updated last month
- 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☆106Updated 6 months ago
- 端到端语音唤醒工具箱,从模型训练到模型推理。☆131Updated last month