Install the dependencies
python -m pip install --user -r requirements.txt
Train the model
python train.py
Test the model
python test.py
Test on a real-world scenario
python app.py
To change your datasets, you can copy them into the train folder. The codes will automatically detect that the folder listed under the train folder is your class label.
You can download the complete dataset here. The dataset consists of 30,000 audio samples of spoken digits (0–9) from 60 different speakers.