Composer AI - Music Generation with LSTM Based RNN

This notebook includes implementation of music generation with LSTM based RNN that covered in MIT 6.S191 Introduction to Deep Learning lab 2.

Data

Dataset is compiled from Cobb's Music of Ireland.

Models

Currently only LSTM based RNN model is exist.

Dependencies

absl-py==0.12.0
astunparse==1.6.3
cachetools==4.2.2
certifi==2020.12.5
chardet==4.0.0
flatbuffers==1.12
gast==0.3.3
google-auth==1.30.0
google-auth-oauthlib==0.4.4
google-pasta==0.2.0
grpcio==1.32.0
h5py==2.10.0
idna==2.10
Keras-Preprocessing==1.1.2
Markdown==3.3.4
numpy==1.19.5
oauthlib==3.1.0
opt-einsum==3.3.0
protobuf==3.17.0
pyasn1==0.4.8
pyasn1-modules==0.2.8
requests==2.25.1
requests-oauthlib==1.3.0
rsa==4.7.2
six==1.15.0
tensorboard==2.5.0
tensorboard-data-server==0.6.1
tensorboard-plugin-wit==1.8.0
tensorflow==2.4.1
tensorflow-estimator==2.4.0
termcolor==1.1.0
tqdm==4.60.0
typing-extensions==3.7.4.3
urllib3==1.26.4
Werkzeug==2.0.0
wrapt==1.12.1
ps: All the libraries can be downloaded by pip install -r requirements.txt

Generated Samples

• https://soundcloud.com/erdem-uysal-578262330/ir-sh-folk-by-lstm-based-rnn
• https://soundcloud.com/erdem-uysal-578262330/irish-folk-by-lstm-based-rnn-2

Blog Post

https://medium.com/analytics-vidhya/music-generation-with-lstm-based-rnn-3fa967bc1f37

Author

R. Erdem Uysal

• https://www.linkedin.com/in/erdemuysal13/
• https://github.com/erd3muysal