I'm a little bit confused about the test set - or the lack thereof. The predictions of which audio files should be submitted? The files in the folder "audiofiles"? But don't we have already the labels for them (and so make it possible to cheat)?
Unless I'm misunderstanding something...
Thank you so much in advance!
The filenames for the audio files that make up the test set are in the SampleSubmission.csv file. The audio_files.zip file contains both audio files for training (whose FileNames are in Train.csv) and also the audio files for which you are expected to make predictions for. Hence your submission should only be comprised of audio files which are in SampleSubmission.csv and not necessarily all files within audio_files.zip.
Ah, that makes sense, thank you so much for your quick reply!