Spoken "Hey Ditto" activation using CNN-LSTM model. Model trained on both synthetic and real human voices along with samples of background noise from various scenes around the world.
- Install required packages:
pip install -r requirements.txt - Run:
python main.pyto test activation on your default mic.
- CNN-LSTM model architecture below with 99% testing accuracy on roughly 30,000 audio samples:
- CNN-LSTM Training Loss:
