{"url":"/dataset/sagalee","name":"Sagalee","full_name":null,"description_markdown":"## Speech Recognition Dataset for Oromo Language.\r\n📊 Key features of Sagalee:\r\n*100 hours of read speech.\r\n*283 gender balanced speakers\r\n* Covers different dialects in Oromo language\r\n* Open source for research","description_withheld":null,"homepage":"","introduced_date":"2025-02-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/sagalee-an-open-source-automatic-speech","title":"Sagalee: an Open Source Automatic Speech Recognition Dataset for Oromo Language","first_author":"Turi Abu","url":null},"license":{"name":"CC BY-NC 4.0 International license","url":"https://creativecommons.org/licenses/by-nc/4.0/legalcode"},"modalities":[{"name":"Audio","url":"/datasets/modality/audio"},{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[{"name":"Automatic Speech Recognition (ASR)","url":"/task/automatic-speech-recognition","datasets_with_task":"/datasets/task/automatic-speech-recognition"}],"languages":[{"name":"Oromo","url":"/datasets/language/oromo"}],"variants":["Sagalee"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/automatic-speech-recognition-asr-on-sagalee","task":"Automatic Speech Recognition (ASR)","dataset_variant":"Sagalee","rows":2,"metrics":["Test WER"],"first_row_in_archive_order":{"model":"Whisper-largev3-finetuned","paper":"/paper/sagalee-an-open-source-automatic-speech","metrics":{"Test WER":"10.82"},"code_links":[{"title":"turinaf/sagalee","url":"https://github.com/turinaf/sagalee"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/sagalee-an-open-source-automatic-speech","title":"Sagalee: an Open Source Automatic Speech Recognition Dataset for Oromo Language","date":"2025-02-01","rows_on_this_dataset":2,"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."}