{"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/gigaspeech-an-evolving-multi-domain-asr","title":"GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio","arxiv_id":"2106.06909","date":"2021-06-13","proceeding":null,"authors":["Guoguo Chen","Shuzhou Chai","Guanbo Wang","Jiayu Du","Wei-Qiang Zhang","Chao Weng","Dan Su","Daniel Povey","Jan Trmal","Junbo Zhang","Mingjie Jin","Sanjeev Khudanpur","Shinji Watanabe","Shuaijiang Zhao","Wei Zou","Xiangang Li","Xuchen Yao","Yongqing Wang","Yujun Wang","Zhao You","Zhiyong Yan"],"abstract":"This paper introduces GigaSpeech, an evolving, multi-domain English speech recognition corpus with 10,000 hours of high quality labeled audio suitable for supervised training, and 40,000 hours of total audio suitable for semi-supervised and unsupervised training. Around 40,000 hours of transcribed audio is first collected from audiobooks, podcasts and YouTube, covering both read and spontaneous speaking styles, and a variety of topics, such as arts, science, sports, etc. A new forced alignment and segmentation pipeline is proposed to create sentence segments suitable for speech recognition training, and to filter out segments with low-quality transcription. For system training, GigaSpeech provides five subsets of different sizes, 10h, 250h, 1000h, 2500h, and 10000h. For our 10,000-hour XL training subset, we cap the word error rate at 4% during the filtering/validation stage, and for all our other smaller training subsets, we cap it at 0%. The DEV and TEST evaluation sets, on the other hand, are re-processed by professional human transcribers to ensure high transcription quality. Baseline systems are provided for popular speech recognition toolkits, namely Athena, ESPnet, Kaldi and Pika.","url_abs":"https://arxiv.org/abs/2106.06909v1","url_pdf":"https://arxiv.org/pdf/2106.06909v1.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":"gigaspeech-an-evolving-multi-domain-asr","repo_url":"https://github.com/SpeechColab/GigaSpeech","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"gigaspeech-an-evolving-multi-domain-asr","repo_url":"https://github.com/maikezuefle/contr-pretraining","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"gigaspeech-an-evolving-multi-domain-asr","repo_url":"https://github.com/speechtranslation/gigas2s","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"CC-BY-4.0"}}],"tasks":[{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[{"slug":"gigaspeech","name":"GigaSpeech","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-recognition-on-gigaspeech","task":"Speech Recognition","dataset":"GigaSpeech","model":"Conformer/Transformer-AED","rank_in_archive_order":1,"of":1,"metrics":{"Word Error Rate (WER)":"10.90"},"uses_additional_data":false},{"leaderboard":"/sota/speech-recognition-on-gigaspeech-dev","task":"Speech Recognition","dataset":"GigaSpeech DEV","model":"Conformer/Transformer-AED","rank_in_archive_order":5,"of":5,"metrics":{"Word Error Rate (WER)":"10.90"},"uses_additional_data":false},{"leaderboard":"/sota/speech-recognition-on-gigaspeech-test","task":"Speech Recognition","dataset":"GigaSpeech TEST","model":"Conformer/Transformer-AED","rank_in_archive_order":5,"of":5,"metrics":{"Word Error Rate (WER)":"10.80"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2106.06909","atlas_url":"https://app.syntology.ai/?focus=2106.06909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.06909"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/speechtranslation/gigas2s","reach":{"status":"ok","spdx":"CC-BY-4.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/maikezuefle/contr-pretraining","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SpeechColab/GigaSpeech","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":3,"ran_fixture":1,"unverified":6},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1},"listed":{"samples":9,"ran":4,"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":"7e03b180fa317c9a","entry":"divide_to_patches","repo":"maikezuefle/contr-pretraining","repo_kind":"listed","path":"llava/mm_utils.py","file_url":"https://github.com/maikezuefle/contr-pretraining/blob/HEAD/llava/mm_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7e03b180fa317c9a"}},{"code_sha256_prefix":"bf62460697adb953","entry":"get_tags_from_arguments","repo":"maikezuefle/contr-pretraining","repo_kind":"listed","path":"llava/wandb_utils.py","file_url":"https://github.com/maikezuefle/contr-pretraining/blob/HEAD/llava/wandb_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bf62460697adb953"}},{"code_sha256_prefix":"2f0311e3c6dd1315","entry":"safe_load_with_env_vars","repo":"maikezuefle/contr-pretraining","repo_kind":"listed","path":"llava/dataset/config.py","file_url":"https://github.com/maikezuefle/contr-pretraining/blob/HEAD/llava/dataset/config.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2f0311e3c6dd1315"}},{"code_sha256_prefix":"3999ff487573f32c","entry":"select_best_resolution","repo":"maikezuefle/contr-pretraining","repo_kind":"listed","path":"llava/mm_utils.py","file_url":"https://github.com/maikezuefle/contr-pretraining/blob/HEAD/llava/mm_utils.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3999ff487573f32c"}},{"code_sha256_prefix":"1d5c013f14c54019","entry":"asr_text_post_processing","repo":"SpeechColab/GigaSpeech","repo_kind":"official","path":"utils/gigaspeech_scoring.py","file_url":"https://github.com/SpeechColab/GigaSpeech/blob/HEAD/utils/gigaspeech_scoring.py","link_basis":"first_harvest_node","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":"1d5c013f14c54019"}},{"code_sha256_prefix":"b6adba723b56d845","entry":"compute_output_length_from_conv1d_hyperparams","repo":"maikezuefle/contr-pretraining","repo_kind":"listed","path":"llava/model/utils.py","file_url":"https://github.com/maikezuefle/contr-pretraining/blob/HEAD/llava/model/utils.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":"b6adba723b56d845"}},{"code_sha256_prefix":"03bdd9034309edfc","entry":"compute_output_length_from_conv1d_layer","repo":"maikezuefle/contr-pretraining","repo_kind":"listed","path":"llava/model/utils.py","file_url":"https://github.com/maikezuefle/contr-pretraining/blob/HEAD/llava/model/utils.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":"03bdd9034309edfc"}},{"code_sha256_prefix":"37899f22fb191b37","entry":"pretty_print_semaphore","repo":"maikezuefle/contr-pretraining","repo_kind":"listed","path":"llava/utils.py","file_url":"https://github.com/maikezuefle/contr-pretraining/blob/HEAD/llava/utils.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":"37899f22fb191b37"}},{"code_sha256_prefix":"d964d4c8ae68d31b","entry":"resize_and_pad_image","repo":"maikezuefle/contr-pretraining","repo_kind":"listed","path":"llava/mm_utils.py","file_url":"https://github.com/maikezuefle/contr-pretraining/blob/HEAD/llava/mm_utils.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":"d964d4c8ae68d31b"}},{"code_sha256_prefix":"f9939a84b9a65279","entry":"violates_moderation","repo":"maikezuefle/contr-pretraining","repo_kind":"listed","path":"llava/utils.py","file_url":"https://github.com/maikezuefle/contr-pretraining/blob/HEAD/llava/utils.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":"f9939a84b9a65279"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}