Our goal is audio classification on the sound.
pip install -r requirements.txt
You can use the dataset that I uploaded on the kaggle site
nbconvert (a jupyter tool for notebook conversion) allows you to do this without any extra packages:
Just go to your terminal and type
jupyter nbconvert --to notebook --inplace --execute make_dataset.ipynb
jupyter nbconvert --to notebook --inplace --execute train.ipynb
You can download the weight of the pre-trained voice classification model from this link