← 开源
shekit

alexa-sign-language-translator

A project to make Amazon Echo respond to sign language using your webcam

ApplicationsOtherJavaScript
在 GitHub 打开
增长势头
+024 小时新增 Star0.0%
501
Star
124
Fork
+0
本周
1
贡献者
创建于 2018-07-28 · 更新于 2026-08-05 · 今日第 18271 名
主要开发者
shekit
README

Making Alexa respond to Sign Language using Tensorflow.js

Try the live demo

Read the Blog Post on Tensorflow's Blog Coming Soon

Watch the video

This project has been shared extensively across social media, and covered in the press: BBC, Verge, Mashable, Fast Co, Kottke, VentureBeat, NowThis and others

Run the demo in latest Chrome/Firefox to train the model using your own words and corresponding signs/gestures. If you have an Echo plugged in closeby, it should respond, otherwise simply play around and have fun. You will need to give permission to access your webcam and microphone.

Running the code

To use the code, first install the JavaScript dependencies by running

npm install

Then start the local budo web server by running

npm start

This will start a web server on localhost:9966.

  1. Allow permission to your webcam and microphone.

  2. Add some words you want to train on.

Reference

To learn more about the classifier used in this repo go to KNN Image Classifier

There is a newer version of this classifier released in the new tensorflow.js which can be found here

排名相邻
同类项目