{"url":"/sota/spoken-language-identification-on","task":{"name":"Spoken language identification","url":"/task/spoken-language-identification","note":null},"dataset":{"name":"VOXLINGUA107","url":"/dataset/voxlingua107"},"category":"Speech","categories":["Speech"],"category_note":null,"description":"Identify the language being spoken from an audio input only.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["0..5sec","5..20sec","Average"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"0..5sec":null,"5..20sec":null,"Average":null}},"counts":{"rows":2,"rows_with_code":0,"rows_with_paper_page":2,"rows_dated":2,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"Noisy","metrics":{"0..5sec":"12.3","5..20sec":"6.1","Average":"7.1"},"uses_additional_data":false,"paper_date":"2020-11-25","paper":"/paper/voxlingua107-a-dataset-for-spoken-language","paper_url":"https://arxiv.org/pdf/2011.12998.pdf","paper_title":"VOXLINGUA107: A DATASET FOR SPOKEN LANGUAGE RECOGNITION","code":null,"n_code_links":0,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":2,"model":"Cleaned","metrics":{"0..5sec":"13.4","5..20sec":"6.6","Average":"7.6"},"uses_additional_data":false,"paper_date":"2020-11-25","paper":"/paper/voxlingua107-a-dataset-for-spoken-language","paper_url":"https://arxiv.org/pdf/2011.12998.pdf","paper_title":"VOXLINGUA107: A DATASET FOR SPOKEN LANGUAGE RECOGNITION","code":null,"n_code_links":0,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":2,"rows_with_any_sample_ran":2,"distinct_papers_with_graph_line":1,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":6,"n_unverified":0,"n_samples":6,"n_pointer_only_licence":6,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}