README.md

metadata

title: BirdCLEF 2024
emoji: 👁
colorFrom: yellow
colorTo: pink
sdk: gradio
sdk_version: 4.36.0
app_file: app.py
pinned: false

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

BirdCLEF 2024: Bird Species Identification from Audio

Overview

This project is part of the BirdCLEF 2024 competition, focusing on identifying bird species from audio recordings. The target region is the Western Ghats, a significant biodiversity hotspot in India. The goal is to develop a machine learning model capable of accurately predicting bird species from audio recordings, with a particular emphasis on under-studied species.

Author

This project was created by:

• Name: LAGHJAJ ABDELLATIF
• Email: [email protected]

Screenshots

Sketch	Main App	Result

Project Components

1. Data Collection
2. Preprocessing
3. Model Training
4. Prediction and Visualization
5. User Interface

Setup Instructions

Prerequisites

Ensure you have the following installed:

• Python 3.8 or higher
• Required Python packages (specified below)

Installation

1. Clone the repository:

   git clone https://github.com/ISEF-soft/introduction-to-machine-learning-challenge-abdellatif-laghjaj
   cd introduction-to-machine-learning-challenge-abdellatif-laghjaj
   

2. Create and activate a virtual environment:

   python -m venv venv
   source venv/bin/activate  # On Windows use `venv\Scripts\activate`
   

3. Install the required packages:

   pip install -r requirements.txt
   

Directory Structure

Ensure your project directory is structured as follows:

birdclef2024/
│
├── sounds/
│ ├── asbfly.ogg
│ ├── bkwsti.ogg
│ └── comros.ogg
│
|── .gitignore
├── model.joblib
├── data.csv
├── app.py
|── main.ipynb
├── README.md
└── requirements.txt

Files Description

• sounds/: Directory containing sample audio files.
• model.joblib: Pre-trained machine learning model.
• data.csv: CSV file containing bird species metadata.
• app.py: Main Python script to run the project.
• main.ipynb: Jupyter notebook containing the project code.
• README.md: This readme file.
• requirements.txt: List of Python packages required.

Running the Project

1. Ensure you have the correct directory structure and all necessary files.
2. Run the app.py script to start the Gradio interface:

   python apy.py
   

Usage

Once the Gradio interface is launched, you can:

• Upload an audio recording of a bird to identify the species.
• Select a sample from the provided audio files.

The interface will display:

• The predicted bird species.
• The prediction confidence.
• A map showing the location of the recording.
• A spectrogram of the audio recording.

Acknowledgements

This project is based on the BirdCLEF 2024 competition. Special thanks to the organizers and contributors who provided the dataset and resources.