{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RTBB62GFVHZCQ74TP6T4EMP4WK","short_pith_number":"pith:RTBB62GF","schema_version":"1.0","canonical_sha256":"8cc21f68c5a9f2287f937fa7c231fcb2a212c130d65eea20efdae10b44d12499","source":{"kind":"arxiv","id":"2307.14743","version":2},"attestation_state":"computed","paper":{"title":"Turning Whisper into Real-Time Transcription System","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dominik Mach\\'a\\v{c}ek, Ond\\v{r}ej Bojar, Raj Dabre","submitted_at":"2023-07-27T10:00:05Z","abstract_excerpt":"Whisper is one of the recent state-of-the-art multilingual speech recognition and translation models, however, it is not designed for real time transcription. In this paper, we build on top of Whisper and create Whisper-Streaming, an implementation of real-time speech transcription and translation of Whisper-like models. Whisper-Streaming uses local agreement policy with self-adaptive latency to enable streaming transcription. We show that Whisper-Streaming achieves high quality and 3.3 seconds latency on unsegmented long-form speech transcription test set, and we demonstrate its robustness an"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2307.14743","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-27T10:00:05Z","cross_cats_sorted":[],"title_canon_sha256":"957b876499edd3a0ed003d191b70a578f54d921528e02d237233aa883cb2ee9e","abstract_canon_sha256":"dee56f2234239ad89926db670d7ed550e20a0879ab9e9534608f8352804adae3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:52:48.936144Z","signature_b64":"wJ5358tr7zs4MzThyGuC/VuTpcYU6DNax14EVhEBlMITu06d8gwrQO0BCZJ7LxfeoGxSHBLIJRpitL8xbm12Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8cc21f68c5a9f2287f937fa7c231fcb2a212c130d65eea20efdae10b44d12499","last_reissued_at":"2026-07-05T06:52:48.935628Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:52:48.935628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Turning Whisper into Real-Time Transcription System","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dominik Mach\\'a\\v{c}ek, Ond\\v{r}ej Bojar, Raj Dabre","submitted_at":"2023-07-27T10:00:05Z","abstract_excerpt":"Whisper is one of the recent state-of-the-art multilingual speech recognition and translation models, however, it is not designed for real time transcription. In this paper, we build on top of Whisper and create Whisper-Streaming, an implementation of real-time speech transcription and translation of Whisper-like models. Whisper-Streaming uses local agreement policy with self-adaptive latency to enable streaming transcription. We show that Whisper-Streaming achieves high quality and 3.3 seconds latency on unsegmented long-form speech transcription test set, and we demonstrate its robustness an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.14743","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2307.14743/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2307.14743","created_at":"2026-07-05T06:52:48.935690+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.14743v2","created_at":"2026-07-05T06:52:48.935690+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.14743","created_at":"2026-07-05T06:52:48.935690+00:00"},{"alias_kind":"pith_short_12","alias_value":"RTBB62GFVHZC","created_at":"2026-07-05T06:52:48.935690+00:00"},{"alias_kind":"pith_short_16","alias_value":"RTBB62GFVHZCQ74T","created_at":"2026-07-05T06:52:48.935690+00:00"},{"alias_kind":"pith_short_8","alias_value":"RTBB62GF","created_at":"2026-07-05T06:52:48.935690+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.12301","citing_title":"WhisperRT -- Turning Whisper into a Causal Streaming Model","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25611","citing_title":"WhisperPipe: A Resource-Efficient Streaming Architecture for Real-Time Automatic Speech Recognition","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RTBB62GFVHZCQ74TP6T4EMP4WK","json":"https://pith.science/pith/RTBB62GFVHZCQ74TP6T4EMP4WK.json","graph_json":"https://pith.science/api/pith-number/RTBB62GFVHZCQ74TP6T4EMP4WK/graph.json","events_json":"https://pith.science/api/pith-number/RTBB62GFVHZCQ74TP6T4EMP4WK/events.json","paper":"https://pith.science/paper/RTBB62GF"},"agent_actions":{"view_html":"https://pith.science/pith/RTBB62GFVHZCQ74TP6T4EMP4WK","download_json":"https://pith.science/pith/RTBB62GFVHZCQ74TP6T4EMP4WK.json","view_paper":"https://pith.science/paper/RTBB62GF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.14743&json=true","fetch_graph":"https://pith.science/api/pith-number/RTBB62GFVHZCQ74TP6T4EMP4WK/graph.json","fetch_events":"https://pith.science/api/pith-number/RTBB62GFVHZCQ74TP6T4EMP4WK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RTBB62GFVHZCQ74TP6T4EMP4WK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RTBB62GFVHZCQ74TP6T4EMP4WK/action/storage_attestation","attest_author":"https://pith.science/pith/RTBB62GFVHZCQ74TP6T4EMP4WK/action/author_attestation","sign_citation":"https://pith.science/pith/RTBB62GFVHZCQ74TP6T4EMP4WK/action/citation_signature","submit_replication":"https://pith.science/pith/RTBB62GFVHZCQ74TP6T4EMP4WK/action/replication_record"}},"created_at":"2026-07-05T06:52:48.935690+00:00","updated_at":"2026-07-05T06:52:48.935690+00:00"}