Parivartan - Audio Enhancement Tool

This project contains a Python script loud_and_clear.py that processes video files to enhance their audio using DeepFilterNet for noise removal and ffmpeg for loudness normalization.

Features

• Extract Audio: Extracts audio from a video file.
• AI Enhancement: Uses DeepFilterNet to remove noise and reconstruct voice.
• Loudness Boost: Normalizes audio loudness to standard levels (I=-16 LUFS) using loudnorm.
• Merge: Merges the enhanced audio back into the original video without re-encoding the video stream.

Prerequisites

• Python 3.8+
• ffmpeg installed and available in your system path.
• DeepFilterNet installed.

Installation

1. Clone the repository.
2. Install dependencies:

   pip install torch torchaudio deepfilternet tqdm

Usage

1. Place your input video in the media folder (or adjust the path in the script).
2. Run the script:

   python loud_and_clear.py

3. The output video will be saved to the specified output path.

Project Structure

• loud_and_clear.py: Main script for audio enhancement.
• main.py: Sample entry point.
• media/: Directory for input and output media files.