/Audio_DeepLearning

Primary LanguageJupyter Notebook

Audio_DeepLearning

Audio Classification with CNN This code is for an audio classification model that uses a Convolutional Neural Network (CNN) to classify audio files from the ESC-50 dataset.

Requirements

The following Python libraries are required:

  • librosa
  • numpy
  • scikit-learn
  • torch
  • torchvision
  • Pillow

These libraries can be installed using the following command:

pip install -r requirements.txt

Acknowledgements

The ESC-50 dataset was created by Karol J. Piczak and is licensed under the Creative Commons Attribution 4.0 International License.