{"url":"/dataset/vietmed","name":"VietMed","full_name":"VietMed: A Dataset and Benchmark for Automatic Speech Recognition of Vietnamese in the Medical Domain","description_markdown":"We introduced a Vietnamese speech recognition dataset in the medical domain comprising 16h of labeled medical speech, 1000h of unlabeled medical speech and 1200h of unlabeled general-domain speech. To our best knowledge, VietMed is by far **the world’s largest public medical speech recognition dataset** in 7 aspects: total duration, number of speakers, diseases, recording conditions, speaker roles, unique medical terms and accents. VietMed is also by far the largest public Vietnamese speech dataset in terms of total duration. Additionally, we are the first to present a medical ASR dataset covering all ICD-10 disease groups and all accents within a country.","description_withheld":null,"homepage":"https://huggingface.co/datasets/leduckhai/VietMed","introduced_date":"2024-04-08","introduced_date_note":null,"introduced_by":{"paper":"/paper/vietmed-a-dataset-and-benchmark-for-automatic","title":"VietMed: A Dataset and Benchmark for Automatic Speech Recognition of Vietnamese in the Medical Domain","first_author":"Khai Le-Duc","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Audio","url":"/datasets/modality/audio"},{"name":"Medical","url":"/datasets/modality/medical"},{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[{"name":"Speech Recognition","url":"/task/speech-recognition","datasets_with_task":"/datasets/task/speech-recognition"},{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"}],"languages":[{"name":"Vietnamese","url":"/datasets/language/vietnamese"}],"variants":["VietMed"],"data_loaders":[{"repo":"https://github.com/leduckhai/multimed","url":"https://github.com/leduckhai/multimed","frameworks":[]}],"num_papers_in_archive":4,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/speech-recognition-on-vietmed","task":"Speech Recognition","dataset_variant":"VietMed","rows":8,"metrics":["Dev WER","Test WER"],"first_row_in_archive_order":{"model":"XLSR-53-Viet","paper":"/paper/vietmed-a-dataset-and-benchmark-for-automatic","metrics":{"Dev WER":"26.8","Test WER":"29.6"},"code_links":[{"title":"leduckhai/multimed","url":"https://github.com/leduckhai/multimed"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/language-modelling-on-vietmed","task":"Language Modelling","dataset_variant":"VietMed","rows":2,"metrics":["PPL"],"first_row_in_archive_order":{"model":"Hybrid 4-gram VietMed-Train + ExtraText","paper":"/paper/vietmed-a-dataset-and-benchmark-for-automatic","metrics":{"PPL":"84"},"code_links":[{"title":"leduckhai/multimed","url":"https://github.com/leduckhai/multimed"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/vietmed-a-dataset-and-benchmark-for-automatic","title":"VietMed: A Dataset and Benchmark for Automatic Speech Recognition of Vietnamese in the Medical Domain","date":"2024-04-08","rows_on_this_dataset":10,"code_links":1,"syntology":null}],"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."}