Convert your own annotations and audio data#
If you start from scratch—with non-annotated audio recording—use the GUI for labelling the data. See the GUI tutorial for a description of all steps - from loading data, annotating song, making a dataset, training a network and generating annotations after training.
However, often annotations exist, from old manual annotations or other tools. You can use existing annotations to train DAS, by converting the existing annotations into the DAS format. See here.