In this repository, I have implemented the concept of sound classification - which is considered as a "Hello World" - type problem for audio deep learning. In this project, we start with a sound file, convert them to the spectrograms, input them into the CNN plus Linear Classifier Model, and produce predictions about the class to which the sound belongs.
.
├── README.md
├── scripts
│ ├── dataSet.py
│ ├── models.py
│ ├── training.py
│ └── utils_functions.py
└── UrbanSound8k
├── fold1
├── fold10
├── fold2
├── fold3
├── fold4
├── fold5
├── fold6
├── fold7
├── fold8
├── fold9
└── metadata
To run this project on your own, follow these steps:
- Clone the repository.
- Create a virtual environment using
python -m venv venv
. - Install the necessary dependencies using
pip install -r requirements.txt
.
Feel free to explore the code and adapt it to your own projects. Enjoy your NLP journey!
Drishya Karki