{"url":"/dataset/jam-alt","name":"Jam-ALT","full_name":"JamALT: A Formatting-Aware Lyrics Transcription Benchmark","description_markdown":"JamALT is a revision of the JamendoLyrics dataset (80 songs in 4 languages), adapted for use as an automatic lyrics transcription (ALT) benchmark.\r\n\r\nThe lyrics have been revised according to the newly compiled [annotation guide](https://huggingface.co/datasets/audioshake/jam-alt/blob/main/GUIDELINES.md), which include rules about spelling, punctuation, and formatting.\r\nThe audio is identical to the JamendoLyrics dataset. However, only 79 songs are included, as one of the 20 French songs has been removed due to concerns about potentially harmful content.","description_withheld":null,"homepage":"https://huggingface.co/datasets/audioshake/jam-alt","introduced_date":"2023-11-09","introduced_date_note":null,"introduced_by":{"paper":"/paper/jam-alt-a-formatting-aware-lyrics","title":"Jam-ALT: A Formatting-Aware Lyrics Transcription Benchmark","first_author":"Ondřej Cífka","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Audio","url":"/datasets/modality/audio"},{"name":"Speech","url":"/datasets/modality/speech"},{"name":"Music","url":"/datasets/modality/music"}],"tasks":[{"name":"Speech Recognition","url":"/task/speech-recognition","datasets_with_task":"/datasets/task/speech-recognition"},{"name":"Automatic Speech Recognition","url":"/task/automatic-speech-recognition-2","datasets_with_task":"/datasets/task/automatic-speech-recognition-2"},{"name":"Automatic Speech Recognition (ASR)","url":"/task/automatic-speech-recognition","datasets_with_task":"/datasets/task/automatic-speech-recognition"},{"name":"Automatic Lyrics Transcription","url":"/task/automatic-lyrics-transcription","datasets_with_task":"/datasets/task/automatic-lyrics-transcription"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"French","url":"/datasets/language/french"},{"name":"Spanish","url":"/datasets/language/spanish"},{"name":"German","url":"/datasets/language/german"}],"variants":["Jam-ALT","Jam-ALT English","Jam-ALT Spanish","Jam-ALT German","Jam-ALT French"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/jamendolyrics/jam-alt","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/audioshake/jam-alt","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":2,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/automatic-lyrics-transcription-on-jam-alt-1","task":"Automatic Lyrics Transcription","dataset_variant":"Jam-ALT English","rows":18,"metrics":["Word Error Rate (WER)","Case-Sensitive Word Error Rate","Case Error Rate","Punctuation F-1","Parenthesis F-1","Line break F-1","Section break F-1"],"first_row_in_archive_order":{"model":"AudioShake v3","paper":"/paper/lyrics-transcription-for-humans-a-readability","metrics":{"Case-Sensitive Word Error Rate":"20.9","Line break F-1":"84.3","Parenthesis F-1":"37.9","Punctuation F-1":"65.3","Section break F-1":"84.8","Word Error Rate (WER)":" 17.3"},"code_links":[{"title":"audioshake/alt-eval","url":"https://github.com/audioshake/alt-eval"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/automatic-lyrics-transcription-on-jam-alt","task":"Automatic Lyrics Transcription","dataset_variant":"Jam-ALT","rows":16,"metrics":["Word Error Rate (WER)","Case-Sensitive Word Error Rate","Case Error Rate","Punctuation F1","Parenthesis F-1","Line break F1","Section break F1"],"first_row_in_archive_order":{"model":"AudioShake v3","paper":"/paper/lyrics-transcription-for-humans-a-readability","metrics":{"Case-Sensitive Word Error Rate":" 20.1","Line break F1":" 84.4","Parenthesis F-1":" 29.4","Punctuation F1":"57.0","Section break F1":"73.9","Word Error Rate (WER)":"16.1"},"code_links":[{"title":"audioshake/alt-eval","url":"https://github.com/audioshake/alt-eval"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/automatic-lyrics-transcription-on-jam-alt-2","task":"Automatic Lyrics Transcription","dataset_variant":"Jam-ALT Spanish","rows":16,"metrics":["Word Error Rate (WER)","Case-Sensitive Word Error Rate","Case Error Rate","Punctuation F-1","Parenthesis F-1","Line break F-1","Section break F-1"],"first_row_in_archive_order":{"model":"AudioShake v3","paper":"/paper/lyrics-transcription-for-humans-a-readability","metrics":{"Case-Sensitive Word Error Rate":"17.7","Line break F-1":"81.5","Parenthesis F-1":" 4.2","Punctuation F-1":" 56.7","Section break F-1":"66.4","Word Error Rate (WER)":"12.6"},"code_links":[{"title":"audioshake/alt-eval","url":"https://github.com/audioshake/alt-eval"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/automatic-lyrics-transcription-on-jam-alt-3","task":"Automatic Lyrics Transcription","dataset_variant":"Jam-ALT German","rows":16,"metrics":["Word Error Rate (WER)","Case-Sensitive Word Error Rate","Case Error Rate","Punctuation F-1","Parenthesis F-1","Line break F-1","Section break F-1"],"first_row_in_archive_order":{"model":"AudioShake v3","paper":"/paper/lyrics-transcription-for-humans-a-readability","metrics":{"Case-Sensitive Word Error Rate":"17.5","Line break F-1":"83.7","Parenthesis F-1":"76.6","Punctuation F-1":" 57.1","Section break F-1":"74.5","Word Error Rate (WER)":"12.6"},"code_links":[{"title":"audioshake/alt-eval","url":"https://github.com/audioshake/alt-eval"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/automatic-lyrics-transcription-on-jam-alt-4","task":"Automatic Lyrics Transcription","dataset_variant":"Jam-ALT French","rows":16,"metrics":["Word Error Rate (WER)","Case-Sensitive Word Error Rate","Case Error Rate","Punctuation F-1","Parenthesis F-1","Line break F-1","Section break F-1"],"first_row_in_archive_order":{"model":"AudioShake v3","paper":"/paper/lyrics-transcription-for-humans-a-readability","metrics":{"Case-Sensitive Word Error Rate":"23.5","Line break F-1":"88.6","Parenthesis F-1":"3.2","Punctuation F-1":"46.1","Section break F-1":"69.0","Word Error Rate (WER)":" 20.8"},"code_links":[{"title":"audioshake/alt-eval","url":"https://github.com/audioshake/alt-eval"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/lyrics-transcription-for-humans-a-readability","title":"Lyrics Transcription for Humans: A Readability-Aware Benchmark","date":"2024-07-30","rows_on_this_dataset":56,"code_links":1,"syntology":null},{"paper":"/paper/jam-alt-a-formatting-aware-lyrics","title":"Jam-ALT: A Formatting-Aware Lyrics Transcription Benchmark","date":"2023-11-23","rows_on_this_dataset":26,"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."}