Mini-project for college

Language identification using machine learning

Live Link: Click Here

Note: The deployment is no longer available as Heroku has discontinued its free plan.

This repository contains the machine learning model for detecting the language of the given text. It has also been developed into a web-app.

Model creation

The dataset is taken from here.

We have used scikit learn library to build the models, train it and test it along with numpy and pandas.

Steps for making the model:

1. Importing the required libraries.

2. Loading the dataset.

3. Data preprocessing - checking for nulls, duplicates, transforming text to lower case, etc.

4. Splitting into training and testing data

5. Training the model on train data.

6. Testing the model on test data.

7. Evaluating the model.

Web App

For making the web-app, we have used HTML, CSS for the frontend and Flask framework for the backend.

Model | Web App repository] | Live link