{"url":"/dataset/vivos","name":"VIVOS","full_name":"VIVOS Corpus","description_markdown":"VIVOS is a free Vietnamese speech corpus consisting of 15 hours of recording speech prepared for Automatic Speech Recognition task.\r\n\r\nThe corpus was prepared by AILAB, a computer science lab of VNUHCM - University of Science, with Prof. Vu Hai Quan is the head of.\r\n\r\nWe publish this corpus in hope to attract more scientists to solve Vietnamese speech recognition problems. The corpus should only be used for academic purposes.","description_withheld":null,"homepage":"https://doi.org/10.5281/zenodo.7068130","introduced_date":"2016-12-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/a-non-expert-kaldi-recipe-for-vietnamese","title":"A non-expert Kaldi recipe for Vietnamese Speech Recognition System","first_author":"Hieu-Thi Luong","url":null},"license":{"name":"CC BY-NC-SA 4.0","url":"https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode"},"modalities":[],"tasks":[{"name":"Speech Recognition","url":"/task/speech-recognition","datasets_with_task":"/datasets/task/speech-recognition"},{"name":"Voice Conversion","url":"/task/voice-conversion","datasets_with_task":"/datasets/task/voice-conversion"}],"languages":[{"name":"Vietnamese","url":"/datasets/language/vietnamese"}],"variants":["VIVOS"],"data_loaders":[],"num_papers_in_archive":7,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/speech-recognition-on-vivos","task":"Speech Recognition","dataset_variant":"VIVOS","rows":3,"metrics":["Test WER"],"first_row_in_archive_order":{"model":"khanhld/chunkformer-large-vie","paper":"/paper/chunkformer-masked-chunking-conformer-for-1","metrics":{"Test WER":"4.18"},"code_links":[{"title":"khanld/chunkformer","url":"https://github.com/khanld/chunkformer"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/wav2vec2-base-vietnamese-160h","title":"Wav2vec2 Base Vietnamese 160h","date":"2022-05-08","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/vietnamese-end-to-end-speech-recognition","title":"Vietnamese end-to-end speech recognition using wav2vec 2.0","date":"2021-09-02","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/chunkformer-masked-chunking-conformer-for-1","title":"ChunkFormer: Masked Chunking Conformer For Long-Form Speech Transcription","date":null,"rows_on_this_dataset":1,"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."}