{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/dataset/libri-light","name":"Libri-Light","full_name":null,"description_markdown":"Libri-Light is a collection of spoken English audio suitable for training speech recognition systems under limited or no supervision. It is derived from open-source audio books from the LibriVox project. It contains over 60K hours of audio.\r\n\r\nSource: [Libri-Light: A Benchmark for ASR with Limited or No Supervision](https://arxiv.org/pdf/1912.07875v1.pdf)","description_withheld":null,"homepage":"https://github.com/facebookresearch/libri-light","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/libri-light-a-benchmark-for-asr-with-limited","title":"Libri-Light: A Benchmark for ASR with Limited or No Supervision","first_author":"Jacob Kahn","url":null},"license":{"name":"Public domain","url":"https://wiki.librivox.org/index.php/Copyright_and_Public_Domain"},"modalities":[],"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"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Libri-Light 60k, test-clean","Libri-Light 60k","Libri-Light test-clean","Libri-Light test-other","Libri-Light"],"data_loaders":[{"repo":"https://github.com/facebookresearch/libri-light","url":"https://github.com/facebookresearch/libri-light","frameworks":[]}],"num_papers_in_archive":194,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/speech-recognition-on-libri-light-test-clean","task":"Speech Recognition","dataset_variant":"Libri-Light test-clean","rows":5,"metrics":["Word Error Rate (WER)","ABX-across","ABX-within"],"first_row_in_archive_order":{"model":"wav2vec 2.0 Large-10h-LV-60k","paper":"/paper/wav2vec-2-0-a-framework-for-self-supervised","metrics":{"Word Error Rate (WER)":"2.5"},"code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"pytorch/fairseq","url":"https://github.com/pytorch/fairseq"},{"title":"pytorch/fairseq","url":"https://github.com/pytorch/fairseq/tree/master/examples/wav2vec"},{"title":"wenet-e2e/wenet","url":"https://github.com/wenet-e2e/wenet"},{"title":"sh-lee-prml/hierspeechpp","url":"https://github.com/sh-lee-prml/hierspeechpp"},{"title":"facebookresearch/brainmagick","url":"https://github.com/facebookresearch/brainmagick"},{"title":"mailong25/vietnamese-speech-recognition","url":"https://github.com/mailong25/vietnamese-speech-recognition"},{"title":"mailong25/self-supervised-speech-recognition","url":"https://github.com/mailong25/self-supervised-speech-recognition"},{"title":"huseinzol05/malaya-speech","url":"https://github.com/huseinzol05/malaya-speech"},{"title":"neonbjb/ocotillo","url":"https://github.com/neonbjb/ocotillo"},{"title":"shivangi-aneja/FaceTalk","url":"https://github.com/shivangi-aneja/FaceTalk"},{"title":"eastonYi/wav2vec","url":"https://github.com/eastonYi/wav2vec"},{"title":"vasudevgupta7/gsoc-wav2vec2","url":"https://github.com/vasudevgupta7/gsoc-wav2vec2"},{"title":"JoungheeKim/Non-Attentive-Tacotron","url":"https://github.com/JoungheeKim/Non-Attentive-Tacotron"},{"title":"HarunoriKawano/Wav2vec2.0","url":"https://github.com/HarunoriKawano/Wav2vec2.0"},{"title":"gatech-eic/s3-router","url":"https://github.com/gatech-eic/s3-router"},{"title":"BirgerMoell/tmh","url":"https://github.com/BirgerMoell/tmh"},{"title":"liutianlin0121/seislm","url":"https://github.com/liutianlin0121/seislm"},{"title":"AIdeaLab/wav2vec2_docker","url":"https://github.com/AIdeaLab/wav2vec2_docker"},{"title":"nlp-en-es/wav2vec2-spanish","url":"https://github.com/nlp-en-es/wav2vec2-spanish"},{"title":"phanxuanphucnd/wav2asr","url":"https://github.com/phanxuanphucnd/wav2asr"},{"title":"Arizona-Voice/Arizona-spotting","url":"https://github.com/Arizona-Voice/Arizona-spotting"},{"title":"phanxuanphucnd/Arizona-spotting","url":"https://github.com/phanxuanphucnd/Arizona-spotting"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/1/wav2vec2_conformer"},{"title":"phanxuanphucnd/Arizona-asr","url":"https://github.com/phanxuanphucnd/Arizona-asr"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-libri-light-test-other","task":"Speech Recognition","dataset_variant":"Libri-Light test-other","rows":5,"metrics":["Word Error Rate (WER)","ABX-across","ABX-within"],"first_row_in_archive_order":{"model":"wav2vec 2.0 Large-10h-LV-60k","paper":"/paper/wav2vec-2-0-a-framework-for-self-supervised","metrics":{"Word Error Rate (WER)":"5.0"},"code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"pytorch/fairseq","url":"https://github.com/pytorch/fairseq"},{"title":"pytorch/fairseq","url":"https://github.com/pytorch/fairseq/tree/master/examples/wav2vec"},{"title":"wenet-e2e/wenet","url":"https://github.com/wenet-e2e/wenet"},{"title":"sh-lee-prml/hierspeechpp","url":"https://github.com/sh-lee-prml/hierspeechpp"},{"title":"facebookresearch/brainmagick","url":"https://github.com/facebookresearch/brainmagick"},{"title":"mailong25/vietnamese-speech-recognition","url":"https://github.com/mailong25/vietnamese-speech-recognition"},{"title":"mailong25/self-supervised-speech-recognition","url":"https://github.com/mailong25/self-supervised-speech-recognition"},{"title":"huseinzol05/malaya-speech","url":"https://github.com/huseinzol05/malaya-speech"},{"title":"neonbjb/ocotillo","url":"https://github.com/neonbjb/ocotillo"},{"title":"shivangi-aneja/FaceTalk","url":"https://github.com/shivangi-aneja/FaceTalk"},{"title":"eastonYi/wav2vec","url":"https://github.com/eastonYi/wav2vec"},{"title":"vasudevgupta7/gsoc-wav2vec2","url":"https://github.com/vasudevgupta7/gsoc-wav2vec2"},{"title":"JoungheeKim/Non-Attentive-Tacotron","url":"https://github.com/JoungheeKim/Non-Attentive-Tacotron"},{"title":"HarunoriKawano/Wav2vec2.0","url":"https://github.com/HarunoriKawano/Wav2vec2.0"},{"title":"gatech-eic/s3-router","url":"https://github.com/gatech-eic/s3-router"},{"title":"BirgerMoell/tmh","url":"https://github.com/BirgerMoell/tmh"},{"title":"liutianlin0121/seislm","url":"https://github.com/liutianlin0121/seislm"},{"title":"AIdeaLab/wav2vec2_docker","url":"https://github.com/AIdeaLab/wav2vec2_docker"},{"title":"nlp-en-es/wav2vec2-spanish","url":"https://github.com/nlp-en-es/wav2vec2-spanish"},{"title":"phanxuanphucnd/wav2asr","url":"https://github.com/phanxuanphucnd/wav2asr"},{"title":"Arizona-Voice/Arizona-spotting","url":"https://github.com/Arizona-Voice/Arizona-spotting"},{"title":"phanxuanphucnd/Arizona-spotting","url":"https://github.com/phanxuanphucnd/Arizona-spotting"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/1/wav2vec2_conformer"},{"title":"phanxuanphucnd/Arizona-asr","url":"https://github.com/phanxuanphucnd/Arizona-asr"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":3,"of":3,"counts":{"papers_with_a_benchmark_row":3,"with_a_code_link":3,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":3,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":2,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/wav2vec-2-0-a-framework-for-self-supervised","slug":"wav2vec-2-0-a-framework-for-self-supervised","title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","date":"2020-06-20","arxiv_id":"2006.11477","rows_on_this_dataset":2,"code_links":25,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":2,"samples_unverified":2,"pointer_only_for_licence":2,"official":{"repos":["pytorch/fairseq"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/wav2vec-2-0-a-framework-for-self-supervised#ran","syntology_url":"https://syntology.ai/paper/2006.11477","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.11477"}}}},{"paper":"/paper/improving-unsupervised-sparsespeech-acoustic","slug":"improving-unsupervised-sparsespeech-acoustic","title":"Improving Unsupervised Sparsespeech Acoustic Models with Categorical Reparameterization","date":"2020-05-29","arxiv_id":"2005.14578","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/libri-light-a-benchmark-for-asr-with-limited","slug":"libri-light-a-benchmark-for-asr-with-limited","title":"Libri-Light: A Benchmark for ASR with Limited or No Supervision","date":"2019-12-17","arxiv_id":"1912.07875","rows_on_this_dataset":6,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":13,"samples_constructed":0,"samples_ran_checked":11,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":14,"official":{"repos":["facebookresearch/libri-light"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/libri-light-a-benchmark-for-asr-with-limited#ran","syntology_url":"https://syntology.ai/paper/1912.07875","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.07875"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/wav2vec-2-0-a-framework-for-self-supervised","slug":"wav2vec-2-0-a-framework-for-self-supervised","title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","date":"2020-06-20","arxiv_id":"2006.11477","rows_on_this_dataset":2,"code_links":25,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":2,"samples_unverified":2,"pointer_only_for_licence":2,"official":{"repos":["pytorch/fairseq"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/wav2vec-2-0-a-framework-for-self-supervised#ran","syntology_url":"https://syntology.ai/paper/2006.11477","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.11477"}}}},{"paper":"/paper/improving-unsupervised-sparsespeech-acoustic","slug":"improving-unsupervised-sparsespeech-acoustic","title":"Improving Unsupervised Sparsespeech Acoustic Models with Categorical Reparameterization","date":"2020-05-29","arxiv_id":"2005.14578","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/libri-light-a-benchmark-for-asr-with-limited","slug":"libri-light-a-benchmark-for-asr-with-limited","title":"Libri-Light: A Benchmark for ASR with Limited or No Supervision","date":"2019-12-17","arxiv_id":"1912.07875","rows_on_this_dataset":6,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":13,"samples_constructed":0,"samples_ran_checked":11,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":14,"official":{"repos":["facebookresearch/libri-light"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/libri-light-a-benchmark-for-asr-with-limited#ran","syntology_url":"https://syntology.ai/paper/1912.07875","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.07875"}}}}],"papers_where_code_ran":2,"papers_where_code_ran_first_page":"/dataset/libri-light/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/libri-light/papers/ran/1","json":"/dataset/libri-light/papers/ran/1.json","rows":2}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":2,"samples_harvested":23,"samples_ran":20,"samples_constructed":0,"samples_ran_checked":16,"samples_ran_instrument_failed":4,"samples_unverified":3,"pointer_only_for_licence":16,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":2,"papers_with_a_run_with_no_instrument_failure":2,"papers_where_every_run_was_an_instrument_failure":0,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"93bd889494e501e4aac868a6b5598d697a2739f0f4a45b0aa21ad31712d1ed8c","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}