2023-07-18 11:55:08 +07:00
2023-07-18 11:50:11 +07:00
2023-07-11 18:40:11 +07:00
2023-07-18 11:50:11 +07:00
2023-07-18 11:50:11 +07:00
2023-07-18 11:55:08 +07:00

Reflector React App

Reflector is a React application that uses WebRTC to stream audio from the browser to a server and receive live transcription and topics from the server.

Table of Contents

Installation

To install the application, run:

npm install

Run the Application

To run the application in development mode, run:

npm run dev

Then open http://localhost:3000 to view it in the browser.

WebRTC Integration

The main part of the WebRTC integration is located in the useWebRTC hook in the hooks/useWebRTC.js file. This hook initiates a WebRTC connection when an audio stream is available, sends signal data to the server, and listens for data from the server.

To connect the application with your server, you need to implement the following:

  1. Signal Data Sending: In the useWebRTC hook, when a 'signal' event is emitted, the hook logs the signal data to the console. You should replace this logging with sending the data to the server:
peer.on('signal', data => {
  // This is where you send the signal data to the server.
});
  1. Data Receiving: The useWebRTC hook listens for 'data' event and when it is emitted, it sets the received data to the data state:
peer.on('data', data => {
  // Received data from the server.
  const serverData = JSON.parse(data.toString());
  setData(serverData);
});

The received data is expected to be a JSON object containing the live transcription and topics:

{
  "transcription": "live transcription...",
  "topics": [
    { "title": "topic 1", "description": "description 1" },
    { "title": "topic 2", "description": "description 2" },
    // ...
  ]
}

This data is then returned from the useWebRTC hook and can be used in your components.

Contribution Guidelines

All new contributions should be made in a separate branch. Before any code is merged into master, it requires a code review by Andreas.

Description
100% local ML models for meeting transcription and analysis
Readme MIT 84 MiB
Languages
Python 72.3%
TypeScript 26.9%
JavaScript 0.3%
Dockerfile 0.2%