MediaXplain

AI-powered Audio & Video Summarizer

---

Table of Contents

• Getting Started
  • Prerequisites
  • Setup before 1st Run
  • Setup before Every Run
  • Run the Application
• Usage
• Built With
• Authors

Getting Started

Follow these instructions to set up and run the application on your local machine.

Prerequisites

• Python -> Installation Guide
• FFmpeg -> Installation Guide

Setup before 1st Run

1. Download the preferred version (latest is recommended) of compressed source folder (zip or tar.gz) from the repository releases.
2. Extract the downloaded folder.
3. Open a terminal and navigate to the project directory

   cd path/to/folder/MediaXplain-x.x.x

4. Set up a virtual environment (optional but recommended)

   python -m venv .venv

5. Activate the virtual environment
   • On Windows

     .venv\Scripts\activate

   • On macOS / Linux

     source .venv/bin/activate

6. Install the required dependencies

   pip install transformers torch textual faster-whisper

Setup before Every Run

1. Navigate to the project directory

   cd path/to/folder/MediaXplain-x.x.x

2. Activate the virtual environment
   • On Windows

     .venv\Scripts\activate

   • On macOS / Linux

     source .venv/bin/activate

Run the Application

Windows

python main.py

macOS / Linux

python3 main.py

Usage

• Enter the absolute path of an audio or a video file you want to summarize.
• Press the "Generate" button to generate the summary.
• View the generated summary in the designated area.
• Copy the summary to clipboard by pressing the "Copy to Clipboard" button.
• Save the summary to a .txt file by pressing the "Save to File" button.

Currently only English audio and video files are supported with accuracy.

Built With

• Python - Core Language
• Textual - TUI Framework
• Transformers - NLP Library
• Torch - Deep Learning Framework
• Faster Whisper - Speech-to-Text Model
• FFmpeg - Media Processing

Authors

• Atia Farha - Frontend Developer
• S.M Nazmus Sadat - Backend Developer