{"url":"/dataset/fsdd","name":"FSDD","full_name":"Free Spoken Digit Dataset","description_markdown":"**Free Spoken Digit Dataset (FSDD)** is a simple audio/speech dataset consisting of recordings of spoken digits in wav files at 8kHz. The recordings are trimmed so that they have near minimal silence at the beginnings and ends. It contains data from 6 speakers, 3,000 recordings (50 of each digit per speaker), and English pronunciations.","description_withheld":null,"homepage":"https://github.com/Jakobovski/free-spoken-digit-dataset","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":{"name":"CC BY-SA 4.0","url":null},"modalities":[{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["FSDD"],"data_loaders":[{"repo":"https://github.com/activeloopai/Hub","url":"https://docs.activeloop.ai/datasets/free-spoken-digit-dataset-fsdd","frameworks":["tf","pytorch"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/spoken_digit","frameworks":["tf","jax"]},{"repo":"https://github.com/Jakobovski/free-spoken-digit-dataset","url":"https://github.com/Jakobovski/free-spoken-digit-dataset","frameworks":[]},{"repo":"https://github.com/Graviti-AI/datasets","url":"https://gas.graviti.com/dataset/graviti/FSDD","frameworks":["tf","pytorch"]}],"num_papers_in_archive":3,"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."}