/Audio-Recognition

This notebook tries to preprocess the .wav files and by generating their spectrogram, we can turn the problem into a image classification problem.

Primary LanguageJupyter Notebook

Audio-Recognition

This notebook tries to preprocess the .wav files and by generating their spectrograms, we can turn the challenge into a image recognition problem. Using Kaggle's API, the datasets from Z by HP Unlocked Challenge 3 can be loaded to Google Colab and a CNN classifier for sound of Capuchin birds with nearly 100% accuracy is built by tensorflow2.