Tzenthin / ASR_python_deploy
基于python的语音识别服务部署,任何一个支持一句话解码的ASR模型接口,都可仿照该框架部署自己的语音识别服务
☆49Updated 2 years ago
Alternatives and similar repositories for ASR_python_deploy:
Users that are interested in ASR_python_deploy are comparing it to the libraries listed below
- 基于FunASR实现语音识别,包含常规版和ONNX版(推荐)。☆28Updated 3 months ago
- ☆29Updated 5 years ago
- 中文标点符号模型,可以给文本添加标点符号。☆134Updated last month
- A enterprise-grade Voice Activity Detector from modelscope and funasr.☆71Updated last year
- 分享在深蓝学院《语音识别:从入门到精通》第一期课程学习过程中完成的课后作业,供参考。☆21Updated 4 years ago
- 主要参考李宏毅老师2020年人类语言处理课程资料整理,包括代码和ppt☆33Updated 3 years ago
- ASR 2Pass onnxruntime and websocket server, based on FunASR(https://github.com/alibaba-damo-academy/FunASR).☆57Updated last month
- 端到端语音唤醒工具箱,从模型训练到模型推理。☆96Updated 4 months ago
- flow mirror models from JZX AI Labs☆42Updated 4 months ago
- ☆15Updated 2 years ago
- PaddleSpeech TTS cpp☆36Updated last year
- Python Wrapper of Silero VAD☆48Updated last month
- ☆44Updated 6 months ago
- Papers of ASR, Tools of ASR☆39Updated last year
- ASR教程: https://dataxujing.github.io/ASR-paper/☆23Updated 6 months ago
- A ctc decoder for both online and offline asr model☆62Updated last year
- ASRT语音识别系统的Python版SDK☆51Updated 2 years ago
- paraformer(chinense asr) online onnx runtime for python☆40Updated 10 months ago
- Chinese text normalization. 中文文本规范化。☆51Updated 3 years ago
- 语音识别模型pytorch转ONNX转MNN,C++实现部署☆52Updated 2 years ago
- Huawei Grad-TTS for Chinese☆46Updated last year
- chinese sentence punctuation prediction,中文句子标点符号预测。☆24Updated 2 years ago
- 本项目使用了EcapaTdnn、ResNetSE、ERes2Net、CAM++等多种先进的声纹识别模型,同时本项目也支持了MelSpectrogram、Spectrogram、MFCC、Fbank等多种数据预处理方法☆247Updated 2 months ago
- A library for adding punctuation into a text from ASR.☆16Updated last year
- ☆37Updated 3 years ago
- 语音识别 论文 前沿☆43Updated 3 years ago
- 一个简单的语音助手框架实现,唤醒词为:“嘿 小二”。(rasa以及自训练的部分遗失了,在框架上适配了对开放平台接口的调用,可根据本地训练的模型对robot中对应功能进行扩展、替换)☆23Updated 5 years ago
- A Bert-CNN-LSTM model for punctuation restoration☆55Updated last year
- 基于标贝数据继续训练,同时对原本的FastSpeech2模型做了改进,引入了韵律表征以及韵律预测模块,使中文发音更生动且富有节奏