This is a prototype Django application that allows users to upload audio files and classify them using machine learning techniques.
GPL-3.0 License
This is a prototype Django application that allows users to upload audio files and classify them using machine learning techniques. The app uses Principal Component Analysis (PCA) for feature reduction and K-Nearest Neighbors (KNN) for classification. The application is designed to be extendable, allowing for the addition of more data and classes in the future.
git clone https://github.com/yourusername/audio_classification.git
cd audio_classification
python -m venv venv
source venv/bin/activate # On Windows use `venv\Scripts\activate`
pip install -r requirements.txt
python manage.py migrate
python manage.py runserver
http://127.0.0.1:8000/
.Upload an Audio File:
View Classification Results:
The application uses the librosa
library to extract MFCC features from the audio files. MFCCs are commonly used in audio processing to represent the short-term power spectrum of a sound.
PCA is used to reduce the dimensionality of the extracted features. This helps in reducing noise and simplifying the data for classification.
A pre-trained KNN model is used to classify the audio files. KNN is a simple, yet effective, classification algorithm that assigns a class based on the majority class of the nearest neighbors.
This application is a prototype and can be extended in several ways:
This project is licensed under the MIT License. See the LICENSE file for details.