{"url":"/dataset/wavcaps","name":"WavCaps","full_name":null,"description_markdown":"A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research.","description_withheld":null,"homepage":"","introduced_date":"2023-03-30","introduced_date_note":null,"introduced_by":{"paper":"/paper/wavcaps-a-chatgpt-assisted-weakly-labelled","title":"WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research","first_author":"Xinhao Mei","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Audio captioning","url":"/task/audio-captioning","datasets_with_task":"/datasets/task/audio-captioning"},{"name":"Text to Audio Retrieval","url":"/task/text-to-audio-retrieval","datasets_with_task":"/datasets/task/text-to-audio-retrieval"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["WavCaps"],"data_loaders":[{"repo":"https://github.com/labbeti/aac-datasets","url":"https://aac-datasets.readthedocs.io/en/stable/","frameworks":["pytorch"]}],"num_papers_in_archive":41,"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":"2026-09-25T09:33:49+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."}