{"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/speechbrain-a-general-purpose-speech-toolkit","title":"SpeechBrain: A General-Purpose Speech Toolkit","arxiv_id":"2106.04624","date":"2021-06-08","proceeding":null,"authors":["Mirco Ravanelli","Titouan Parcollet","Peter Plantinga","Aku Rouhe","Samuele Cornell","Loren Lugosch","Cem Subakan","Nauman Dawalatabad","Abdelwahab Heba","Jianyuan Zhong","Ju-chieh Chou","Sung-Lin Yeh","Szu-Wei Fu","Chien-Feng Liao","Elena Rastorgueva","François Grondin","William Aris","Hwidong Na","Yan Gao","Renato de Mori","Yoshua Bengio"],"abstract":"SpeechBrain is an open-source and all-in-one speech toolkit. It is designed to facilitate the research and development of neural speech processing technologies by being simple, flexible, user-friendly, and well-documented. This paper describes the core architecture designed to support several tasks of common interest, allowing users to naturally conceive, compare and share novel speech processing pipelines. SpeechBrain achieves competitive or state-of-the-art performance in a wide range of speech benchmarks. It also provides training recipes, pretrained models, and inference scripts for popular speech datasets, as well as tutorials which allow anyone with basic Python proficiency to familiarize themselves with speech technologies.","url_abs":"https://arxiv.org/abs/2106.04624v1","url_pdf":"https://arxiv.org/pdf/2106.04624v1.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":"speechbrain-a-general-purpose-speech-toolkit","repo_url":"https://github.com/speechbrain/speechbrain","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"speechbrain-a-general-purpose-speech-toolkit","repo_url":"https://github.com/guxm2021/MM_ALT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"speechbrain-a-general-purpose-speech-toolkit","repo_url":"https://github.com/guxm2021/alt_speechbrain","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"speechbrain-a-general-purpose-speech-toolkit","repo_url":"https://github.com/guxm2021/svt_speechbrain","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"language-identification","task_name":"Language Identification"},{"task_slug":"spoken-language-understanding","task_name":"Spoken Language Understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.04624","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.04624"}},"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/guxm2021/svt_speechbrain","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/speechbrain/speechbrain","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/guxm2021/alt_speechbrain","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/guxm2021/MM_ALT","reach":null}],"summary":{"unverified":7},"by_repo_kind":{"listed":{"samples":7,"ran":0,"repositories":1}},"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":0,"samples":[{"code_sha256_prefix":"7860cf2775dccb29","entry":"ctc_loss","repo":"guxm2021/svt_speechbrain","repo_kind":"listed","path":"speechbrain/nnet/losses.py","file_url":"https://github.com/guxm2021/svt_speechbrain/blob/HEAD/speechbrain/nnet/losses.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7860cf2775dccb29"}},{"code_sha256_prefix":"8feeecfbeb765eab","entry":"get_padding_elem","repo":"guxm2021/svt_speechbrain","repo_kind":"listed","path":"speechbrain/nnet/CNN.py","file_url":"https://github.com/guxm2021/svt_speechbrain/blob/HEAD/speechbrain/nnet/CNN.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8feeecfbeb765eab"}},{"code_sha256_prefix":"26b6efc761f6e025","entry":"get_padding_elem_transposed","repo":"guxm2021/svt_speechbrain","repo_kind":"listed","path":"speechbrain/nnet/CNN.py","file_url":"https://github.com/guxm2021/svt_speechbrain/blob/HEAD/speechbrain/nnet/CNN.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"26b6efc761f6e025"}},{"code_sha256_prefix":"4d856b195967f759","entry":"pack_padded_sequence","repo":"guxm2021/svt_speechbrain","repo_kind":"listed","path":"speechbrain/nnet/RNN.py","file_url":"https://github.com/guxm2021/svt_speechbrain/blob/HEAD/speechbrain/nnet/RNN.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4d856b195967f759"}},{"code_sha256_prefix":"7c9d9bad06c577fb","entry":"pad_packed_sequence","repo":"guxm2021/svt_speechbrain","repo_kind":"listed","path":"speechbrain/nnet/RNN.py","file_url":"https://github.com/guxm2021/svt_speechbrain/blob/HEAD/speechbrain/nnet/RNN.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7c9d9bad06c577fb"}},{"code_sha256_prefix":"85608dd83e84cc4e","entry":"parse_arguments","repo":"guxm2021/svt_speechbrain","repo_kind":"listed","path":"speechbrain/core.py","file_url":"https://github.com/guxm2021/svt_speechbrain/blob/HEAD/speechbrain/core.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"85608dd83e84cc4e"}},{"code_sha256_prefix":"1fab9869e1f0ddf0","entry":"transducer_loss","repo":"guxm2021/svt_speechbrain","repo_kind":"listed","path":"speechbrain/nnet/losses.py","file_url":"https://github.com/guxm2021/svt_speechbrain/blob/HEAD/speechbrain/nnet/losses.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1fab9869e1f0ddf0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}