{"url":"/dataset/the-peoples-speech","name":"The People’s Speech","full_name":null,"description_markdown":"**The People's Speech** is a free-to-download 30,000-hour and growing supervised conversational English speech recognition dataset licensed for academic and commercial usage under CC-BY-SA (with a CC-BY subset). The data is collected via searching the Internet for appropriately licensed audio data with existing transcriptions.","description_withheld":null,"homepage":"https://github.com/mlcommons/peoples-speech","introduced_date":"2021-11-17","introduced_date_note":null,"introduced_by":{"paper":"/paper/the-people-s-speech-a-large-scale-diverse","title":"The People's Speech: A Large-Scale Diverse English Speech Recognition Dataset for Commercial Usage","first_author":"Daniel Galvez","url":null},"license":{"name":"CC-BY-SA","url":null},"modalities":[{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[],"languages":[],"variants":["The People’s Speech"],"data_loaders":[],"num_papers_in_archive":7,"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."}