{"url":"/dataset/ted-lium-3","name":"TED-LIUM","full_name":null,"description_markdown":"The TED-LIUM corpus consists of English-language TED talks. It includes transcriptions of these talks. The audio is sampled at 16kHz. The dataset spans a range of 118 to 452 hours of transcribed speech data.","description_withheld":null,"homepage":"https://www.openslr.org/51/","introduced_date":"2012-05-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/ted-lium-an-automatic-speech-recognition","title":"TED-LIUM: an Automatic Speech Recognition dedicated corpus","first_author":"Anthony Rousseau","url":null},"license":{"name":"CC BY-NC-ND 3.0","url":"https://creativecommons.org/licenses/by-nc-nd/3.0/"},"modalities":[{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Speech Recognition","url":"/task/speech-recognition","datasets_with_task":"/datasets/task/speech-recognition"},{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"},{"name":"Automatic Speech Recognition","url":"/task/automatic-speech-recognition-2","datasets_with_task":"/datasets/task/automatic-speech-recognition-2"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["TED-LIUM","Tedlium"],"data_loaders":[{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/tedlium","frameworks":["tf","jax"]},{"repo":"https://github.com/pytorch/audio","url":"https://pytorch.org/audio/stable/datasets.html#torchaudio.datasets.TEDLIUM","frameworks":["pytorch"]}],"num_papers_in_archive":64,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/speech-recognition-on-tedlium","task":"Speech Recognition","dataset_variant":"Tedlium","rows":4,"metrics":["Word Error Rate (WER)"],"first_row_in_archive_order":{"model":"United-MedASR (764M)","paper":"/paper/high-precision-medical-speech-recognition","metrics":{"Word Error Rate (WER)":"0.29"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-ted-lium","task":"Speech Recognition","dataset_variant":"TED-LIUM","rows":2,"metrics":["Word Error Rate (WER)"],"first_row_in_archive_order":{"model":"Whisper-LLaMa-7b","paper":"/paper/hyporadise-an-open-baseline-for-generative-1","metrics":{"Word Error Rate (WER)":"4.6"},"code_links":[{"title":"hypotheses-paradise/hypo2trans","url":"https://github.com/hypotheses-paradise/hypo2trans"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/high-precision-medical-speech-recognition","title":"High-precision medical speech recognition through synthetic data and semantic correction: UNITED-MEDASR","date":"2024-11-24","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/hyporadise-an-open-baseline-for-generative-1","title":"HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models","date":"2023-09-27","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":3,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/fast-conformer-with-linearly-scalable","title":"Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition","date":"2023-05-08","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/bigssl-exploring-the-frontier-of-large-scale","title":"BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition","date":"2021-09-27","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/speechstew-simply-mix-all-available-speech","title":"SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network","date":"2021-04-05","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":7,"samples_ran":3,"samples_unverified":4,"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."}