The Data

Orchestrate's music generation model was trained on a database of over 30,000 MIDI files drawn from two datasets, ComMU and MetaMIDI.

Licenses & User Agreements

The ComMU dataset is released under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License (CC BY-NC-SA 4.0). It is provided primarily for research purposes and is prohibited for commercial use.

The MetaMIDI dataset contains some copyrighted music files and therefore cannot be used for commercial purposes without specific approval. A list of the copyright meta-events is provided in the dataset to acknowledge the original authors of the files.

Product Pipeline & Infrastructure

NLP Process

If you are interested in learning more about the actual implementation of Orchestrate or are interested in training and running these models yourself, feel free to check out our GitHub link.