{"url":"/sota/speech-recognition-on-common-voice-french","task":{"name":"Speech Recognition","url":"/task/speech-recognition","note":null},"dataset":{"name":"Common Voice French","url":"/dataset/common-voice"},"category":"Audio","categories":["Audio","Speech"],"category_note":null,"description":"**Speech Recognition** is the task of converting spoken language into text. It involves recognizing the words spoken in an audio recording and transcribing them into a written format. The goal is to accurately transcribe the speech in real-time or from recorded audio, taking into account factors such as accents, speaking speed, and background noise.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [SpecAugment](https://arxiv.org/pdf/1904.08779v2.pdf) )</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Test WER"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Test WER":"lower"}},"counts":{"rows":8,"rows_with_code":8,"rows_with_paper_page":8,"rows_dated":8,"rows_using_additional_data":7},"rows":[{"rank_in_archive_order":1,"model":"ConformerCTC-L (5-gram)","metrics":{"Test WER":"8.13%"},"uses_additional_data":true,"paper_date":"2021-10-15","paper":"/paper/scribosermo-fast-speech-to-text-models-for","paper_url":"https://arxiv.org/abs/2110.07982v1","paper_title":"Scribosermo: Fast Speech-to-Text models for German and other Languages","code":"https://gitlab.com/Jaco-Assistant/deepspeech-polyglot","n_code_links":3,"syntology":null},{"rank_in_archive_order":2,"model":"ConformerCTC-L (4-gram)","metrics":{"Test WER":"9.16%"},"uses_additional_data":true,"paper_date":"2019-09-14","paper":"/paper/nemo-a-toolkit-for-building-ai-applications","paper_url":"https://arxiv.org/abs/1909.09577v1","paper_title":"NeMo: a toolkit for building AI applications using Neural Modules","code":"https://github.com/NVIDIA/NeMo","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"VoxPopuli-50K (n-gram)","metrics":{"Test WER":"9.6%"},"uses_additional_data":true,"paper_date":"2021-01-02","paper":"/paper/voxpopuli-a-large-scale-multilingual-speech","paper_url":"https://arxiv.org/abs/2101.00390v2","paper_title":"VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation","code":"https://github.com/facebookresearch/voxpopuli","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":4,"model":"ConformerCTC-L (no-LM)","metrics":{"Test WER":"9.63%"},"uses_additional_data":true,"paper_date":"2019-09-14","paper":"/paper/nemo-a-toolkit-for-building-ai-applications","paper_url":"https://arxiv.org/abs/1909.09577v1","paper_title":"NeMo: a toolkit for building AI applications using Neural Modules","code":"https://github.com/NVIDIA/NeMo","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"ConformerCTC-L (no-LM)","metrics":{"Test WER":"10.19 %"},"uses_additional_data":true,"paper_date":"2021-10-15","paper":"/paper/scribosermo-fast-speech-to-text-models-for","paper_url":"https://arxiv.org/abs/2110.07982v1","paper_title":"Scribosermo: Fast Speech-to-Text models for German and other Languages","code":"https://gitlab.com/Jaco-Assistant/deepspeech-polyglot","n_code_links":3,"syntology":null},{"rank_in_archive_order":6,"model":"QuartzNet15x5FR (D7)","metrics":{"Test WER":"11.0%"},"uses_additional_data":true,"paper_date":"2021-10-15","paper":"/paper/scribosermo-fast-speech-to-text-models-for","paper_url":"https://arxiv.org/abs/2110.07982v1","paper_title":"Scribosermo: Fast Speech-to-Text models for German and other Languages","code":"https://gitlab.com/Jaco-Assistant/deepspeech-polyglot","n_code_links":3,"syntology":null},{"rank_in_archive_order":7,"model":"QuartzNet15x5FR (CV-only)","metrics":{"Test WER":"12.1%"},"uses_additional_data":false,"paper_date":"2021-10-15","paper":"/paper/scribosermo-fast-speech-to-text-models-for","paper_url":"https://arxiv.org/abs/2110.07982v1","paper_title":"Scribosermo: Fast Speech-to-Text models for German and other Languages","code":"https://gitlab.com/Jaco-Assistant/deepspeech-polyglot","n_code_links":3,"syntology":null},{"rank_in_archive_order":8,"model":"Whisper (Large v2)","metrics":{"Test WER":"13.9%"},"uses_additional_data":true,"paper_date":"2022-12-06","paper":"/paper/robust-speech-recognition-via-large-scale-1","paper_url":"https://arxiv.org/abs/2212.04356v1","paper_title":"Robust Speech Recognition via Large-Scale Weak Supervision","code":"https://github.com/huggingface/transformers","n_code_links":15,"syntology":{"n_ran":42,"n_unverified":17,"n_samples":59,"n_pointer_only_licence":18}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 7,081 of the 9,623 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9623,"papers_checked":7081,"papers_extracted_not_yet_verified":217,"boards_without_verdict":27,"papers_not_yet_extracted":2325},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":2,"rows_with_any_sample_ran":2,"distinct_papers_with_graph_line":2,"distinct_papers_with_any_sample_ran":2,"samples_over_distinct_papers":{"n_ran":43,"n_unverified":17,"n_samples":60,"n_pointer_only_licence":19,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":43,"n_unverified":17,"n_samples":60,"n_pointer_only_licence":19,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}