**train_audio/** The training data consists of short recordings of individual bird calls generously uploaded by users of xenocanto.org. These files have been downsampled to 32 kHz where applicable to match the test set audio and converted to the ogg format. The training data should have nearly all relevant files; we expect there is no benefit to looking for more on xenocanto.org. **test_soundscapes/** When you submit a notebook, the test_soundscapes directory will be populated with approximately 200 recordings to be used for scoring. They are 10 minutes long and in ogg audio format. The file names are randomized. It should take your submission notebook approximately five minutes to load all of the test soundscapes. **train_metadata.csv** A wide range of metadata is provided for the training data. **sample_submission.csv** A valid sample submission. **eBird_Taxonomy_v2021.csv** Data on the relationships between different species.