All Projects → OAID → Cortex M Kws

OAID / Cortex M Kws

Licence: apache-2.0
Cortex M KWS example with Tengine Lite.

Programming Languages

c
50402 projects - #5 most used programming language

Projects that are alternatives of or similar to Cortex M Kws

Automatic speech recognition
End-to-end Automatic Speech Recognition for Madarian and English in Tensorflow
Stars: ✭ 2,751 (+6013.33%)
Mutual labels:  cnn, speech-recognition
Keras Sincnet
Keras (tensorflow) implementation of SincNet (Mirco Ravanelli, Yoshua Bengio - https://github.com/mravanelli/SincNet)
Stars: ✭ 47 (+4.44%)
Mutual labels:  cnn, speech-recognition
Asrt speechrecognition
A Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统
Stars: ✭ 4,943 (+10884.44%)
Mutual labels:  cnn, speech-recognition
Awesome Speech Recognition Speech Synthesis Papers
Automatic Speech Recognition (ASR), Speaker Verification, Speech Synthesis, Text-to-Speech (TTS), Language Modelling, Singing Voice Synthesis (SVS), Voice Conversion (VC)
Stars: ✭ 2,085 (+4533.33%)
Mutual labels:  cnn, speech-recognition
Nmtpytorch
Sequence-to-Sequence Framework in PyTorch
Stars: ✭ 392 (+771.11%)
Mutual labels:  cnn, speech-recognition
Rhino
On-device speech-to-intent engine powered by deep learning
Stars: ✭ 406 (+802.22%)
Mutual labels:  cortex-m, speech-recognition
Sincnet
SincNet is a neural architecture for efficiently processing raw audio samples.
Stars: ✭ 764 (+1597.78%)
Mutual labels:  cnn, speech-recognition
Ijjs
a lightweight js runtime for IOT(一个面向物联网的JS运行时)
Stars: ✭ 38 (-15.56%)
Mutual labels:  cnn
Monodepth360
Master's project implementing depth estimation for spherical images using unsupervised learning with CNNs.
Stars: ✭ 41 (-8.89%)
Mutual labels:  cnn
Twitter Sentiment Analysis
Sentiment analysis on tweets using Naive Bayes, SVM, CNN, LSTM, etc.
Stars: ✭ 978 (+2073.33%)
Mutual labels:  cnn
Neural Networks
All about Neural Networks!
Stars: ✭ 34 (-24.44%)
Mutual labels:  cnn
Mc Cnn Python
a python implementation of MC-CNN
Stars: ✭ 38 (-15.56%)
Mutual labels:  cnn
Yann
This toolbox is support material for the book on CNN (http://www.convolution.network).
Stars: ✭ 41 (-8.89%)
Mutual labels:  cnn
Discordspeechbot
A speech-to-text bot for discord with music commands and more using NodeJS. Ideally for controlling your Discord server using voice commands, can also be useful for hearing-impaired people.
Stars: ✭ 35 (-22.22%)
Mutual labels:  speech-recognition
Avsr Deep Speech
Google Summer of Code 2017 Project: Development of Speech Recognition Module for Red Hen Lab
Stars: ✭ 43 (-4.44%)
Mutual labels:  speech-recognition
Covidaid
COVID-19 Detection Using Chest X-Ray
Stars: ✭ 35 (-22.22%)
Mutual labels:  cnn
Mirror
Matchable Image Retrieval by Learning from Surface Reconstruction
Stars: ✭ 44 (-2.22%)
Mutual labels:  cnn
Chineseidcardocr
[Deprecated] 🇨🇳中国二代身份证光学识别
Stars: ✭ 1,015 (+2155.56%)
Mutual labels:  cnn
Pncc
A implementation of Power Normalized Cepstral Coefficients: PNCC
Stars: ✭ 40 (-11.11%)
Mutual labels:  speech-recognition
Keras basic
keras를 이용한 딥러닝 기초 학습
Stars: ✭ 39 (-13.33%)
Mutual labels:  cnn

Cortex-M-KWS

简介

Cortex-M-KWSOPEN AI LAB 主导开发,该项目主要用于基于 Cortex-M4 核心的微控制通过 Tengine Lite 推理框架简单部署关键词识别(KWS, Keyword Spotting)的功能。方便开发者进行技术评估。

开发环境

硬件需求

  • STM32F469I-DISCO:STM32F469I开发评估套件(基于 Cortex-M4 核心)

软件需求

  • Keil IDE
  • CMSIS
  • FreeRTOS
  • Tengine Lite

运行说明

  • Keil IDE 安装

    • 完成 Keil-MDK 5.3 安装。
  • 下载本项目

git clone  https://github.com/OAID/cortex-m-kws.git
  • 编译及烧写

    • 使用 Keil-MDK 打开工程文件

      cortex-m-kws/Projects/STM32469I-Discovery/Applications/AID_newmodel/aid_speech/MDK-ARM/Project.uvprojx

    • 完成依赖库自动安装;

    • 使用 USB 连接电脑和开发板;

    • 编译工程,生成 hex 文件;

    • 下载 hex 文件至开发板。

关键词

本项目包含11个关键词,分别是:小智小智、打开窗帘、关闭窗帘、打开空调、关闭空调、加热模式、制冷模式、降低温度、调高温度、开启扫风、启动空调。

致谢

Cortex-M-KWS 参考和借鉴了下列项目:

License

技术讨论

  • Github issues
  • QQ 群: 829565581
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].