A naive program that listens to you and determines your mood when you speak to it. The model is trained on the RAVDESS
and TESS
datasets and features a many-to-one LSTM classifier.
- Python 3.6.X, the program is tested and developed in
- PyTorch, which can be installed with the following command:
pip3 install https://download.pytorch.org/whl/cu90/torch-1.1.0-cp36-cp36m-win_amd64.whl
- PyAudio, install with the following instructions
- librosa
- [OPTIONAL]
tensorboard
for visualizing training progress