The full development set is approximately 6.5 GB .
The dataset is hosted by the and can be accessed through platforms like Zenodo . Download 736 740 zip
Visit the DCASE Automated Audio Captioning task page for the most recent version (v2.1). The full development set is approximately 6
If you are writing a technical report or paper using this data, ensure you include these standard sections: Download 736 740 zip
You can also download specific evaluation (1.2 GB) or analysis (14.4 GB) subsets. 🛠️ Producing a Write-up