C++ library to apply similarity measures and classifications on the results of audio analysis, including Python bindings. Together with Essentia it can be used to compute high-level descriptions of music.
Sometimes you may want to create a project then edit the generated project file before actually doing the training. It would be good to add a flag --notrain or --create-only to just create the project and then stop before doing the training.
The next time you run train_model without this flag it should pick up the existing project and train the model as expected.
dbogdanov
commented
4 years ago
Sometimes you may want to create a project then edit the generated project file before actually doing the training. It would be good to add a flag
--notrainor--create-onlyto just create the project and then stop before doing the training. The next time you runtrain_modelwithout this flag it should pick up the existing project and train the model as expected.