{"url":"/dataset/voxforge-german","name":"Voxforge German","full_name":null,"description_markdown":"VoxForge is an open speech dataset that was set up to collect transcribed speech for use with Free and  Open Source Speech Recognition Engines (on Linux, Windows and Mac). \r\n\r\nWe will make available all submitted audio files under the GPL license, and then 'compile' them into acoustic models for use with Open Source speech recognition engines such as CMU Sphinx, ISIP, Julius (github) and HTK (note: HTK has distribution restrictions).","description_withheld":null,"homepage":"http://www.voxforge.org/de","introduced_date":"2006-10-10","introduced_date_note":null,"introduced_by":null,"license":{"name":"GPL","url":"http://www.voxforge.org/home/docs/faq/faq/what-is-gpl"},"modalities":[{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Automatic Speech Recognition (ASR)","url":"/task/automatic-speech-recognition","datasets_with_task":"/datasets/task/automatic-speech-recognition"}],"languages":[{"name":"German","url":"/datasets/language/german"}],"variants":["Voxforge German"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/automatic-speech-recognition-on-voxforge","task":"Automatic Speech Recognition (ASR)","dataset_variant":"Voxforge German","rows":1,"metrics":["WER (%)"],"first_row_in_archive_order":{"model":"Conformer Transducer","paper":"/paper/automatic-speech-recognition-in-german-a","metrics":{"WER (%)":"3.36%"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/automatic-speech-recognition-in-german-a","title":"Automatic Speech Recognition in German: A Detailed Error Analysis","date":"2022-08-03","rows_on_this_dataset":1,"code_links":0,"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."}