{"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":"/paper/scribosermo-fast-speech-to-text-models-for","title":"Scribosermo: Fast Speech-to-Text models for German and other Languages","arxiv_id":"2110.07982","date":"2021-10-15","proceeding":null,"authors":["Daniel Bermuth","Alexander Poeppel","Wolfgang Reif"],"abstract":"Recent Speech-to-Text models often require a large amount of hardware resources and are mostly trained in English. This paper presents Speech-to-Text models for German, as well as for Spanish and French with special features: (a) They are small and run in real-time on microcontrollers like a RaspberryPi. (b) Using a pretrained English model, they can be trained on consumer-grade hardware with a relatively small dataset. (c) The models are competitive with other solutions and outperform them in German. In this respect, the models combine advantages of other approaches, which only include a subset of the presented features. Furthermore, the paper provides a new library for handling datasets, which is focused on easy extension with additional datasets and shows an optimized way for transfer-learning new languages using a pretrained model from another language with a similar alphabet.","url_abs":"https://arxiv.org/abs/2110.07982v1","url_pdf":"https://arxiv.org/pdf/2110.07982v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"scribosermo-fast-speech-to-text-models-for","repo_url":"https://gitlab.com/jaco-assistant/scribosermo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"scribosermo-fast-speech-to-text-models-for","repo_url":"https://gitlab.com/jaco-assistant/corcua","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"scribosermo-fast-speech-to-text-models-for","repo_url":"https://gitlab.com/Jaco-Assistant/deepspeech-polyglot","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-to-text","task_name":"Speech-to-Text"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-recognition-on-common-voice-french","task":"Speech Recognition","dataset":"Common Voice French","model":"ConformerCTC-L (5-gram)","rank_in_archive_order":1,"of":8,"metrics":{"Test WER":"8.13%"},"uses_additional_data":true},{"leaderboard":"/sota/speech-recognition-on-common-voice-french","task":"Speech Recognition","dataset":"Common Voice French","model":"ConformerCTC-L (no-LM)","rank_in_archive_order":5,"of":8,"metrics":{"Test WER":"10.19 %"},"uses_additional_data":true},{"leaderboard":"/sota/speech-recognition-on-common-voice-french","task":"Speech Recognition","dataset":"Common Voice French","model":"QuartzNet15x5FR (D7)","rank_in_archive_order":6,"of":8,"metrics":{"Test WER":"11.0%"},"uses_additional_data":true},{"leaderboard":"/sota/speech-recognition-on-common-voice-french","task":"Speech Recognition","dataset":"Common Voice French","model":"QuartzNet15x5FR (CV-only)","rank_in_archive_order":7,"of":8,"metrics":{"Test WER":"12.1%"},"uses_additional_data":false},{"leaderboard":"/sota/speech-recognition-on-common-voice-german","task":"Speech Recognition","dataset":"Common Voice German","model":"ConformerCTC-L (5-gram)","rank_in_archive_order":3,"of":14,"metrics":{"Test CER":"1.37%","Test WER":"4.05%"},"uses_additional_data":true},{"leaderboard":"/sota/speech-recognition-on-common-voice-german","task":"Speech Recognition","dataset":"Common Voice German","model":"QuartzNet15x5DE (D37, 5-gram)","rank_in_archive_order":8,"of":14,"metrics":{"Test CER":"2.7%","Test WER":"6.6%"},"uses_additional_data":true},{"leaderboard":"/sota/speech-recognition-on-common-voice-german","task":"Speech Recognition","dataset":"Common Voice German","model":"ConformerCTC-L (no LM)","rank_in_archive_order":10,"of":14,"metrics":{"Test CER":"2.05%","Test WER":"7.33%"},"uses_additional_data":true},{"leaderboard":"/sota/speech-recognition-on-common-voice-german","task":"Speech Recognition","dataset":"Common Voice German","model":"QuartzNet15x5DE (CV-only, 5-gram)","rank_in_archive_order":11,"of":14,"metrics":{"Test CER":"3.2%","Test WER":"7.7%"},"uses_additional_data":false},{"leaderboard":"/sota/speech-recognition-on-common-voice-italian","task":"Speech Recognition","dataset":"Common Voice Italian","model":"QuartzNet15x5IT (D5)","rank_in_archive_order":2,"of":2,"metrics":{"Test WER":"11.5%"},"uses_additional_data":true},{"leaderboard":"/sota/speech-recognition-on-common-voice-spanish","task":"Speech Recognition","dataset":"Common Voice Spanish","model":"ConformerCTC-L (5-gram)","rank_in_archive_order":3,"of":8,"metrics":{"Test WER":"5.68%"},"uses_additional_data":true},{"leaderboard":"/sota/speech-recognition-on-common-voice-spanish","task":"Speech Recognition","dataset":"Common Voice Spanish","model":"ConformerCTC-L (no-LM)","rank_in_archive_order":5,"of":8,"metrics":{"Test WER":"7.46 %"},"uses_additional_data":true},{"leaderboard":"/sota/speech-recognition-on-common-voice-spanish","task":"Speech Recognition","dataset":"Common Voice Spanish","model":"QuartzNet15x5ES (D8)","rank_in_archive_order":6,"of":8,"metrics":{"Test WER":"10.0%"},"uses_additional_data":true},{"leaderboard":"/sota/speech-recognition-on-common-voice-spanish","task":"Speech Recognition","dataset":"Common Voice Spanish","model":"QuartzNet15x5ES (CV-only)","rank_in_archive_order":8,"of":8,"metrics":{"Test WER":"10.5%"},"uses_additional_data":false},{"leaderboard":"/sota/speech-recognition-on-tuda","task":"Speech Recognition","dataset":"TUDA","model":"QuartzNet15x5DE (D37)","rank_in_archive_order":3,"of":9,"metrics":{"Test WER":"10.2%"},"uses_additional_data":true}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"gitlab.com/jaco-assistant/scribosermo","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"gitlab.com/jaco-assistant/corcua","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"gitlab.com/Jaco-Assistant/deepspeech-polyglot","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"7fc7246f8fe666bcea9811a765154696a67f30f70957be3208d5c68024e8c796","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}