Video Transcription & Translation System

Description

This project is a full-stack, AI-powered application designed to transcribe spoken content from MP4 video files and translate it into a user-selected target language. It provides a web interface for uploading videos and receiving translated transcripts, leveraging asynchronous processing for efficiency.

Technical Report

Click here

Architecture

Demo Video

How to Install

Prerequisites

• Docker Desktop
• An OpenAI API Key

Installation Steps

1. Clone the repository:

   git clone https://github.com/Wassim-Hamra/TahoAI_Challenge.git
   cd TahoAI_Challenge

2. Create backend/backend.env: Navigate into your backend directory:

   cd backend

   Create a file named backend.env in this directory and add your OpenAI API key:

   OPENAI_API_KEY=sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
   

   Replace sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx with your actual OpenAI API Key. Then, navigate back to the project root:

   cd ..

3. Build and Run with Docker Compose: From the root directory of the project (where docker-compose.yml is located), run:

   docker-compose up --build

   This command will:

   • Build the Docker images for both your backend and frontend.
   • Start Redis, the Django backend server, the Celery worker, and the Next.js development server.

Accessing the Application

Once docker-compose up is running, the application will be accessible:

• Frontend (Web UI): Open your browser and navigate to http://localhost:3000

Monitoring

• To view logs from all running services:

  docker-compose logs -f

• To view logs from a specific service (e.g., backend or celery_worker):

  docker-compose logs -f backend
  docker-compose logs -f celery_worker

Shutdown

To stop all running services, press Ctrl+C in the terminal where docker-compose up is running.

here's a video you can test the application with

---

Created by Wassim Hamra