HumanScreamingDetection is a Python-based application designed to detect human screaming sounds in audio data. This project uses machine learning techniques, specifically with a focus on audio processing, to identify screaming sounds. It can be applied in various safety and monitoring systems.
Clone the repository and install the required dependencies:
git clone https://github.com/whats2000/HumanScreamingDetection.git
cd HumanScreamingDetection
pip install -r requirements.txt
To download the dataset, you have two options:
- Directly from Kaggle: Human Screaming Detection Dataset
- Using the provided Jupyter notebooks:
- Download control audio data:
HumanScreamingDetection/DownloadControlAudioData.ipynb - Download sample audio data:
HumanScreamingDetection/DownloadSampleAudioData.ipynb
- Download control audio data:
The data cleaning and preprocessing methods are detailed in the Jupyter notebook HumanScreamingDetection/TransformData.ipynb.
The model training process is conducted in the notebook HumanScreamingDetection/Resnet34Train.ipynb.
To run the application, navigate to the AppForTesting directory and execute App.py:
cd AppForTesting
python App.py
Contributions to the HumanScreamingDetection project are welcome.
This project is licensed under the GPL-3.0 license License - see the LICENSE file for details.
For any queries or contributions, please contact Create Issue here.