{"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/tevr-improving-speech-recognition-by-token","title":"TEVR: Improving Speech Recognition by Token Entropy Variance Reduction","arxiv_id":"2206.12693","date":"2022-06-25","proceeding":null,"authors":["Hajo Nils Krabbenhöft","Erhardt Barth"],"abstract":"This paper presents TEVR, a speech recognition model designed to minimize the variation in token entropy w.r.t. to the language model. This takes advantage of the fact that if the language model will reliably and accurately predict a token anyway, then the acoustic model doesn't need to be accurate in recognizing it. We train German ASR models with 900 million parameters and show that on CommonVoice German, TEVR scores a very competitive 3.64% word error rate, which outperforms the best reported results by a relative 16.89% reduction in word error rate. We hope that releasing our fully trained speech recognition pipeline to the community will lead to privacy-preserving offline virtual assistants in the future.","url_abs":"https://arxiv.org/abs/2206.12693v1","url_pdf":"https://arxiv.org/pdf/2206.12693v1.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":"tevr-improving-speech-recognition-by-token","repo_url":"https://github.com/DeutscheKI/tevr-asr-tool","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"tevr-improving-speech-recognition-by-token","repo_url":"https://huggingface.co/fxtentacle/wav2vec2-xls-r-1b-tevr","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"automatic-speech-recognition","task_name":"Automatic Speech Recognition (ASR)"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"privacy-preserving","task_name":"Privacy Preserving"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-recognition-on-common-voice-german","task":"Speech Recognition","dataset":"Common Voice German","model":"wav2vec 2.0 XLS-R 1B + TEVR (5-gram)","rank_in_archive_order":1,"of":14,"metrics":{"Test CER":"1.54%","Test WER":"3.64%"},"uses_additional_data":true},{"leaderboard":"/sota/speech-recognition-on-common-voice-german","task":"Speech Recognition","dataset":"Common Voice German","model":"wav2vec 2.0 XLS-R 1B + TEVR (4-gram)","rank_in_archive_order":2,"of":14,"metrics":{"Test WER":"3.70%"},"uses_additional_data":true},{"leaderboard":"/sota/speech-recognition-on-common-voice-german","task":"Speech Recognition","dataset":"Common Voice German","model":"wav2vec 2.0 XLS-R 1B (5-gram)","rank_in_archive_order":4,"of":14,"metrics":{"Test CER":"1.62%","Test WER":"4.38%"},"uses_additional_data":true},{"leaderboard":"/sota/speech-recognition-on-common-voice-german","task":"Speech Recognition","dataset":"Common Voice German","model":"wav2vec 2.0 XLS-R 1B + TEVR (no LM)","rank_in_archive_order":13,"of":14,"metrics":{"Test WER":"10.10%"},"uses_additional_data":true},{"leaderboard":"/sota/speech-recognition-on-common-voice-german","task":"Speech Recognition","dataset":"Common Voice German","model":"wav2vec 2.0 XLS-R (no LM)","rank_in_archive_order":14,"of":14,"metrics":{"Test WER":"12.06%"},"uses_additional_data":false}],"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":"DeutscheKI/tevr-asr-tool","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"huggingface.co/fxtentacle/wav2vec2-xls-r-1b-tevr","kind":"official","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":"26e023d8ad42c8fde7ebe506e7df44bc74461e4c579fe76047bff927c2b62242","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}