Skip to content

The intelligent chatroom with toxicity detection and speech to text ability.

Notifications You must be signed in to change notification settings

tipped73/chatroom

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

19 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Submission Details

Name: Ashutosh Chauhan

University: IIT Jammu

Department: Electrical Engineering

Design Document: https://docs.google.com/document/d/1BRMRRii3Edt42wU9_Xz48_6is0S0kZUt069RupbArec/edit?usp=sharing

Smart Chat

A chatroom where users can interact with the room through text messages. It supports the censoring of toxic words. The following category of messages is censored by the toxicity model integrated into the chat app, identity attacks, insults, obscene, severe toxicity, sexually explicit, and threats. It also provides functions such as writing a new message by speaking (speech to text) and auto-reading of new messages (text to speech).

Installation instructions:

Enable speech to text api on google cloud console, then create a service account and download its json file. The file should be placed inside the api folder.

Clone this repository locally.
git clone https://github.com/ashutoshc8101/chatroom.git

Install dependencies

cd api;
npm install
mv .env.example .env
cd ../app
npm install

Update the mongodb username and password in the .env file.

To run the web app locally, use the following commands:

cd api;
npm run start;
cd ../app;
npm run start;

Live Demo

A demo is deployed on http://13.235.177.229/. The speech to text functionality is not working in the demo as it requires a https connection.

Demo Video

smart-chat-2022-11-02_12.35.38.mp4

Speech Recognition

Enable speech recogition on Google Cloud Console and create a service account. Download serviceAccount.json and place it in api folder.

About

The intelligent chatroom with toxicity detection and speech to text ability.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • JavaScript 92.9%
  • HTML 6.4%
  • CSS 0.7%