{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/espresso-a-fast-end-to-end-neural-speech","title":"Espresso: A Fast End-to-end Neural Speech Recognition Toolkit","arxiv_id":"1909.08723","date":"2019-09-18","proceeding":null,"authors":["Yiming Wang","Tongfei Chen","Hainan Xu","Shuoyang Ding","Hang Lv","Yiwen Shao","Nanyun Peng","Lei Xie","Shinji Watanabe","Sanjeev Khudanpur"],"abstract":"We present Espresso, an open-source, modular, extensible end-to-end neural automatic speech recognition (ASR) toolkit based on the deep learning library PyTorch and the popular neural machine translation toolkit fairseq. Espresso supports distributed training across GPUs and computing nodes, and features various decoding approaches commonly employed in ASR, including look-ahead word-based language model fusion, for which a fast, parallelized decoder is implemented. Espresso achieves state-of-the-art ASR performance on the WSJ, LibriSpeech, and Switchboard data sets among other end-to-end systems without data augmentation, and is 4--11x faster for decoding than similar systems (e.g. ESPnet).","url_abs":"https://arxiv.org/abs/1909.08723v3","url_pdf":"https://arxiv.org/pdf/1909.08723v3.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":"espresso-a-fast-end-to-end-neural-speech","repo_url":"https://github.com/freewym/espresso","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"automatic-speech-recognition-2","task_name":"Automatic Speech Recognition"},{"task_slug":"automatic-speech-recognition","task_name":"Automatic Speech Recognition (ASR)"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-recognition-on-hub500-callhome","task":"Speech Recognition","dataset":"Hub5'00 CallHome","model":"Espresso","rank_in_archive_order":1,"of":1,"metrics":{"Word Error Rate (WER)":"19.1"},"uses_additional_data":false},{"leaderboard":"/sota/speech-recognition-on-hub500-switchboard","task":"Speech Recognition","dataset":"Hub5'00 SwitchBoard","model":"Espresso","rank_in_archive_order":5,"of":5,"metrics":{"Eval2000":"9.2"},"uses_additional_data":false},{"leaderboard":"/sota/speech-recognition-on-librispeech-test-clean","task":"Speech Recognition","dataset":"LibriSpeech test-clean","model":"Espresso","rank_in_archive_order":44,"of":64,"metrics":{"Word Error Rate (WER)":"2.8"},"uses_additional_data":false},{"leaderboard":"/sota/speech-recognition-on-librispeech-test-other","task":"Speech Recognition","dataset":"LibriSpeech test-other","model":"Espresso","rank_in_archive_order":44,"of":53,"metrics":{"Word Error Rate (WER)":"8.7"},"uses_additional_data":false},{"leaderboard":"/sota/speech-recognition-on-wsj-eval92","task":"Speech Recognition","dataset":"WSJ eval92","model":"Espresso","rank_in_archive_order":10,"of":17,"metrics":{"Word Error Rate (WER)":"3.4"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1909.08723","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.08723"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/freewym/espresso","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"bbe1a698e337d4d4","entry":"get_symbols_to_strip_from_output","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"bbe1a698e337d4d4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}