{"url":"/dataset/midicaps","name":"MidiCaps","full_name":"MidiCaps","description_markdown":"The MidiCaps dataset [1] is a large-scale dataset of 168,385 midi music files with descriptive text captions, and a set of extracted musical features.\r\n\r\nThe captions have been produced through a captioning pipeline incorporating MIR feature extraction and LLM Claude 3 to caption the data from extracted features with an in-context learning task. The framework used to extract the captions is available open source on github. The original MIDI files originate from the Lakh MIDI Dataset [2,3] and are creative commons licenced.","description_withheld":null,"homepage":"https://huggingface.co/datasets/amaai-lab/MidiCaps","introduced_date":"2024-06-04","introduced_date_note":null,"introduced_by":{"paper":"/paper/midicaps-a-large-scale-midi-dataset-with-text","title":"MidiCaps: A large-scale MIDI dataset with text captions","first_author":"Jan Melechovsky","url":null},"license":{"name":"CC","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Midi","url":"/datasets/modality/midi"}],"tasks":[{"name":"Music Generation","url":"/task/music-generation","datasets_with_task":"/datasets/task/music-generation"},{"name":"Music Captioning","url":"/task/music-captioning","datasets_with_task":"/datasets/task/music-captioning"}],"languages":[],"variants":["MidiCaps"],"data_loaders":[],"num_papers_in_archive":6,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}