Whale detection using audio clips

The collection of whale sound audio files was converted into numpy files for easy readability by Python, with spectrograms created for better visualization. Features such as Mel-Frequency Cepstral Coefficients (MFCC), spectral roll-off, and spectral centroid were extracted from the data and fed into a Convolutional Neural Network (CNN) model for training. 80% of the data was used for training, while the remaining 20% was used to test the model's accuracy.

The final model had an accuracy of over 98%. The training was perfomed on the GPUs on the Ozstar cluster.