Essentia is a reference open-source C++/Python library for audio and music analysis. In this work, we present a set of algorithms that employ TensorFlow in Essentia that allow predictions with pre-trained deep learning models — and some of those are based on musicnn!
To show the potential of this new interface with TensorFlow, we provide a number of pre-trained state-of-the-art music tagging and classification CNN models. We run an extensive evaluation of the developed models. In particular, we assess the generalization capabilities in a cross-collection evaluation utilizing both external tag datasets as well as manual annotations tailored to the taxonomies of our models.
On the personal side, I’m happy to have finally contributed to Essentia. After sharing the office with Dimitry and Pablo (main developers of Essentia) for years, I really wanted to bring the models I developed during my PhD to Essentia. Now, thanks to the amazing work by Pablo and Dmitry, we have musicnn (and others!) in Essentia 🙂