Tzenthin / wenet_mnnLinks
语音识别模型pytorch转ONNX转MNN,C++实现部署
☆82Updated 3 years ago
Alternatives and similar repositories for wenet_mnn
Users that are interested in wenet_mnn are comparing it to the libraries listed below
Sorting:
- 端到端语音唤醒工具箱,从模型训练到模型推理。☆144Updated 4 months ago
- A enterprise-grade Voice Activity Detector from modelscope and funasr.☆120Updated 2 years ago
- ASR 2Pass onnxruntime and websocket server, based on FunASR(https://github.com/alibaba-damo-academy/FunASR).☆91Updated last month
- ☆75Updated 3 years ago
- ☆33Updated 4 years ago
- A library for adding punctuation into a text from ASR.☆19Updated 2 years ago
- ☆40Updated 4 years ago
- paraformer(chinense asr) online onnx runtime for python☆53Updated last year
- IndexTTS Fine-tuning notebooks☆121Updated 6 months ago
- A Tiny Project For ASR model training and Deployment☆27Updated 3 years ago
- PaddleSpeech TTS cpp☆43Updated 2 years ago
- Port of Funasr's Paraformer model in C/C++☆39Updated last year
- TTS appalication based on modelscope KAN-TTS☆41Updated last year
- ☆142Updated 2 years ago
- 修复funasr中seaco-paraformer导出onnx后没有时间戳的bug☆23Updated last year
- A lightweight pure C++ Text-to-Speech (TTS) pipeline with OpenVINO, supporting multiple languages.☆87Updated 3 months ago
- Utilizes ONNX Runtime for audio denoising.☆102Updated last week
- ☆69Updated last year
- some ncnn demos of FunASR☆28Updated last year
- 达摩fsmn vad c++推理服务☆18Updated 2 years ago
- TTS inference in C++ based on TFlite model☆20Updated 4 years ago
- Python的音频工具☆16Updated 3 weeks ago
- C/C++实现Python音频处理库librosa中melspectrogram的计算过程☆31Updated 3 years ago
- Utilizes ONNX Runtime to transcribe audio into text.☆63Updated this week
- Python Wrapper of Silero VAD☆63Updated 7 months ago
- Utilizes ONNX Runtime for speech activity detection.☆38Updated 2 weeks ago
- SenseVoice-python: A enterprise-grade open source multi-language asr system from funasr opensource with onnxruntime☆108Updated 2 months ago
- Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.☆20Updated 8 months ago
- 基于FunASR实现语音识别,包含常规版和ONNX版(推荐)。☆46Updated last year
- 从Kaldi中裁剪的轻量级语音识别解码推理框架,目前实现了MFCC+GMM+Viterbi,不依赖OpenFST、OpenBLAS等库☆22Updated 4 years ago