{"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/golos-russian-dataset-for-speech-research","title":"Golos: Russian Dataset for Speech Research","arxiv_id":"2106.10161","date":"2021-06-18","proceeding":null,"authors":["Nikolay Karpov","Alexander Denisenko","Fedor Minkin"],"abstract":"This paper introduces a novel Russian speech dataset called Golos, a large corpus suitable for speech research. The dataset mainly consists of recorded audio files manually annotated on the crowd-sourcing platform. The total duration of the audio is about 1240 hours. We have made the corpus freely available to download, along with the acoustic model with CTC loss prepared on this corpus. Additionally, transfer learning was applied to improve the performance of the acoustic model. In order to evaluate the quality of the dataset with the beam-search algorithm, we have built a 3-gram language model on the open Common Crawl dataset. The total word error rate (WER) metrics turned out to be about 3.3% and 11.5%.","url_abs":"https://arxiv.org/abs/2106.10161v1","url_pdf":"https://arxiv.org/pdf/2106.10161v1.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":"golos-russian-dataset-for-speech-research","repo_url":"https://github.com/sberdevices/golos","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"golos-russian-dataset-for-speech-research","repo_url":"https://github.com/1hb6s7t/contrib","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok","spdx":"Apache-2.0"}}],"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":"transfer-learning","task_name":"Transfer Learning"}],"methods":[{"method_slug":"ctc-loss","method_name":"CTC Loss"}],"datasets_introduced":[{"slug":"golos","name":"GOLOS","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2106.10161","atlas_url":"https://app.syntology.ai/?focus=2106.10161","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.10161"}},"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/sberdevices/golos","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/1hb6s7t/contrib","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_violates":1,"ran_draft_wrong":2,"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"repositories":1},"listed":{"samples":2,"ran":2,"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":3,"samples":[{"code_sha256_prefix":"aa5486a3650902d8","entry":"exists","repo":"1hb6s7t/contrib","repo_kind":"listed","path":"application/Adaptive-Nesterov-Momentum-Algorithm/adan.py","file_url":"https://github.com/1hb6s7t/contrib/blob/HEAD/application/Adaptive-Nesterov-Momentum-Algorithm/adan.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"aa5486a3650902d8"}},{"code_sha256_prefix":"04d2c814d175b5ed","entry":"infer_greedy","repo":"sberdevices/golos","repo_kind":"official","path":"examples/infer.py","file_url":"https://github.com/sberdevices/golos/blob/HEAD/examples/infer.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"04d2c814d175b5ed"}},{"code_sha256_prefix":"5e2ed23acb71ee11","entry":"noop","repo":"1hb6s7t/contrib","repo_kind":"listed","path":"application/Fixup-Initialization/model_build.py","file_url":"https://github.com/1hb6s7t/contrib/blob/HEAD/application/Fixup-Initialization/model_build.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5e2ed23acb71ee11"}},{"code_sha256_prefix":"b63285ba26f9de94","entry":"read_file_list","repo":"sberdevices/golos","repo_kind":"official","path":"examples/infer.py","file_url":"https://github.com/sberdevices/golos/blob/HEAD/examples/infer.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b63285ba26f9de94"}},{"code_sha256_prefix":"dca50e2137822994","entry":"infer_beam_search_lm","repo":"sberdevices/golos","repo_kind":"official","path":"examples/infer.py","file_url":"https://github.com/sberdevices/golos/blob/HEAD/examples/infer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dca50e2137822994"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}