{"url":"/dataset/voxlingua107","name":"VOXLINGUA107","full_name":null,"description_markdown":"Language Identification Dataset","description_withheld":null,"homepage":"","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[{"name":"Spoken language identification","url":"/task/spoken-language-identification","datasets_with_task":"/datasets/task/spoken-language-identification"},{"name":"Language Identification","url":"/task/language-identification","datasets_with_task":"/datasets/task/language-identification"}],"languages":[],"variants":["VOXLINGUA107"],"data_loaders":[],"num_papers_in_archive":2,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/language-identification-on-voxlingua107-1","task":"Language Identification","dataset_variant":"VOXLINGUA107","rows":2,"metrics":["Error rate"],"first_row_in_archive_order":{"model":"XLS-R","paper":"/paper/xls-r-self-supervised-cross-lingual-speech","metrics":{"Error rate":"5.7"},"code_links":[{"title":"pytorch/fairseq","url":"https://github.com/pytorch/fairseq"},{"title":"gatech-eic/s3-router","url":"https://github.com/gatech-eic/s3-router"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/spoken-language-identification-on","task":"Spoken language identification","dataset_variant":"VOXLINGUA107","rows":2,"metrics":["0..5sec","5..20sec","Average"],"first_row_in_archive_order":{"model":"Noisy","paper":"/paper/voxlingua107-a-dataset-for-spoken-language","metrics":{"0..5sec":"12.3","5..20sec":"6.1","Average":"7.1"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/xls-r-self-supervised-cross-lingual-speech","title":"XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale","date":"2021-11-17","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/voxlingua107-a-dataset-for-spoken-language","title":"VOXLINGUA107: A DATASET FOR SPOKEN LANGUAGE RECOGNITION","date":"2020-11-25","rows_on_this_dataset":2,"code_links":0,"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."}