Skip to content

Latest commit

 

History

History
34 lines (23 loc) · 738 Bytes

README.md

File metadata and controls

34 lines (23 loc) · 738 Bytes

Sound Classification

This recurrent neural network tries to differentiate between sounds. The RNN is trained by using example data provided in the repo. in Sound-Data folder.


Installation

> - Clone Repository
> - Install Dependencies

Training

> - python main.py -m train

Testing

> - python main.py -m pred -u <model ID from trained model here>

Dependiencies

tensorflow
numpy
librosa
matplotlib
tqdm
uuid

Example

The RNN successfully classificated 1.wav as label 0 in class dictionary img_pred