{"url":"/dataset/npsc","name":"NPSC","full_name":"Norwegian Parliamentary Speech Corpus","description_markdown":"The Norwegian Parliamentary Speech Corpus (NPSC) is a speech corpus made by the Norwegian Language Bank at the National Library of Norway in 2019-2021. The NPSC consists of recordings of speech from Stortinget, the Norwegian parliament, and corresponding orthographic transcriptions to Norwegian Bokmål and Norwegian Nynorsk. All transcriptions are done manually by trained linguists or philologists, and the manual transcriptions are subsequently proofread to ensure consistency and accuracy. Entire days of Parliamentary meetings are transcribed in the dataset.","description_withheld":null,"homepage":"https://www.nb.no/sprakbanken/en/resource-catalogue/oai-nb-no-sbr-58/","introduced_date":"2022-01-26","introduced_date_note":null,"introduced_by":{"paper":"/paper/the-norwegian-parliamentary-speech-corpus","title":"The Norwegian Parliamentary Speech Corpus","first_author":"Per Erik Solberg","url":null},"license":{"name":"CC-ZERO","url":"https://www.nb.no/sprakbanken/en/resource-catalogue/oai-nb-no-sbr-58/#resource-common-info"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[{"name":"Automatic Speech Recognition","url":"/task/automatic-speech-recognition-2","datasets_with_task":"/datasets/task/automatic-speech-recognition-2"},{"name":"Automatic Speech Recognition (ASR)","url":"/task/automatic-speech-recognition","datasets_with_task":"/datasets/task/automatic-speech-recognition"}],"languages":[{"name":"Norwegian Nynorsk","url":"/datasets/language/norwegian-nynorsk"},{"name":"Norwegian Bokmål","url":"/datasets/language/norwegian-bokm-l"}],"variants":["NPSC"],"data_loaders":[],"num_papers_in_archive":2,"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."}