As the semester comes to an end, so too does the Orchestrator project. The blog hasn’t been updated in a while, but we’ve been hard at work on some cool final projects!

Replicating the paper’s experiment with in and out of domain samples with the pretrained model and .wav samples we collected on our own

We make our own music classifier with librosa and learn about formatting musical data into tensors we can work with.

Note: The code had an error, so it was only training one decoder :( So these results are not very significant. See also https://github.com/facebookresearch/music-translation/issues/7 and https://github.com/facebookresearch/music-translation/issues/15

Finish setting up network on CSUA + team check-ins

Team check-ins, ToneNet

Basic rundown of how to modify this website

Paper overview and teams

Started Pytorch tutorial, set up CSUA accounts, SSH access, and Jupyter