{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IEEOFDJCIX665ZIYTWE2ZMQAUC","short_pith_number":"pith:IEEOFDJC","schema_version":"1.0","canonical_sha256":"4108e28d2245fdeee5189d89acb200a097357136fd05fac01ebfaa47593e90f0","source":{"kind":"arxiv","id":"2303.00747","version":2},"attestation_state":"computed","paper":{"title":"WhisperX: Time-Accurate Speech Transcription of Long-Form Audio","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Andrew Zisserman, Jaesung Huh, Max Bain, Tengda Han","submitted_at":"2023-03-01T18:59:13Z","abstract_excerpt":"Large-scale, weakly-supervised speech recognition models, such as Whisper, have demonstrated impressive results on speech recognition across domains and languages. However, their application to long audio transcription via buffered or sliding window approaches is prone to drifting, hallucination & repetition; and prohibits batched transcription due to their sequential nature. Further, timestamps corresponding each utterance are prone to inaccuracies and word-level timestamps are not available out-of-the-box. To overcome these challenges, we present WhisperX, a time-accurate speech recognition "},"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":"2303.00747","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-03-01T18:59:13Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"23c58f308c76257ad80d23edf27046bc7e21d88fdd276bd2a3daffad9b0c40de","abstract_canon_sha256":"d717a89aca48732172a543a3d72b0645121eca44cf8b6f025bac519bb51efdaf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:29:41.862296Z","signature_b64":"ruKJhD3EFgvKtg8rQMAS9V4nQx2CQSo4xzQIwnJ3j/9X6gbsMa2TYXacgvUfzU2AfVkX7XI53lgQ4YewtZaPBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4108e28d2245fdeee5189d89acb200a097357136fd05fac01ebfaa47593e90f0","last_reissued_at":"2026-07-05T06:29:41.861803Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:29:41.861803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WhisperX: Time-Accurate Speech Transcription of Long-Form Audio","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Andrew Zisserman, Jaesung Huh, Max Bain, Tengda Han","submitted_at":"2023-03-01T18:59:13Z","abstract_excerpt":"Large-scale, weakly-supervised speech recognition models, such as Whisper, have demonstrated impressive results on speech recognition across domains and languages. However, their application to long audio transcription via buffered or sliding window approaches is prone to drifting, hallucination & repetition; and prohibits batched transcription due to their sequential nature. Further, timestamps corresponding each utterance are prone to inaccuracies and word-level timestamps are not available out-of-the-box. To overcome these challenges, we present WhisperX, a time-accurate speech recognition "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.00747","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/2303.00747/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":"2303.00747","created_at":"2026-07-05T06:29:41.861861+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.00747v2","created_at":"2026-07-05T06:29:41.861861+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.00747","created_at":"2026-07-05T06:29:41.861861+00:00"},{"alias_kind":"pith_short_12","alias_value":"IEEOFDJCIX66","created_at":"2026-07-05T06:29:41.861861+00:00"},{"alias_kind":"pith_short_16","alias_value":"IEEOFDJCIX665ZIY","created_at":"2026-07-05T06:29:41.861861+00:00"},{"alias_kind":"pith_short_8","alias_value":"IEEOFDJC","created_at":"2026-07-05T06:29:41.861861+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.09831","citing_title":"AI-Driven Analytics of Team-Teaching Talk: Acoustic Patterns across Experience, Cohorts and the Learning Design","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2606.23060","citing_title":"From Text Metrics to Model Internals: A Study of Whisper ASR Hallucination Detection","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21661","citing_title":"UnityShots: Memory-Driven Multi-Shot Audio-Video Generation with Boundary-Aware Gating","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18466","citing_title":"Montreal Forced Aligner and the state of speech-to-text alignment in 2026","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07397","citing_title":"Audio-Oscar: A Multi-Agent System for Complex Audio Scene Generation, Orchestration, and Refinement","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30993","citing_title":"SwanVoice: Expressive Long-Form Zero-Shot Speech Synthesis for Both Monologue and Dialogue","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28480","citing_title":"Audio-Mind: An Auditable Agentic Framework for Audio Understanding","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31069","citing_title":"Towards Effective Long-Video Event Prediction via Multi-Level Event Semantics Mining","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23043","citing_title":"Deviance from a pink noise regime in the temporal organization of semantic relations in psychosis","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22732","citing_title":"Beyond Acoustic Emotion Recognition: Multimodal Pathos Analysis in Political Speech Using LLM-Based and Acoustic Emotion Models","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21132","citing_title":"SurgOnAir: Hierarchy-Aware Real-Time Surgical Video Commentary","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16555","citing_title":"MedASR: An Open-Source Model for High-Accuracy Medical Dictation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27010","citing_title":"Quantifying the Cost of Manual Navigation: A Comparison of Gesture-Based Magnification versus Direct Access Reading in Digital Layout-based Documents","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24416","citing_title":"Scaling Properties of Continuous Diffusion Spoken Language Models","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23295","citing_title":"Human-1 by Josh Talks: A Full-Duplex Conversational Modeling Framework in Hindi using Real-World Conversations","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10456","citing_title":"A Benchmark and Multi-Agent System for Instruction-driven Cinematic Video Compilation","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06694","citing_title":"AudioKV: KV Cache Eviction in Efficient Large Audio Language Models","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15736","citing_title":"RefereeBench: Are Video MLLMs Ready to be Multi-Sport Referees","ref_index":4,"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":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IEEOFDJCIX665ZIYTWE2ZMQAUC","json":"https://pith.science/pith/IEEOFDJCIX665ZIYTWE2ZMQAUC.json","graph_json":"https://pith.science/api/pith-number/IEEOFDJCIX665ZIYTWE2ZMQAUC/graph.json","events_json":"https://pith.science/api/pith-number/IEEOFDJCIX665ZIYTWE2ZMQAUC/events.json","paper":"https://pith.science/paper/IEEOFDJC"},"agent_actions":{"view_html":"https://pith.science/pith/IEEOFDJCIX665ZIYTWE2ZMQAUC","download_json":"https://pith.science/pith/IEEOFDJCIX665ZIYTWE2ZMQAUC.json","view_paper":"https://pith.science/paper/IEEOFDJC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.00747&json=true","fetch_graph":"https://pith.science/api/pith-number/IEEOFDJCIX665ZIYTWE2ZMQAUC/graph.json","fetch_events":"https://pith.science/api/pith-number/IEEOFDJCIX665ZIYTWE2ZMQAUC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IEEOFDJCIX665ZIYTWE2ZMQAUC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IEEOFDJCIX665ZIYTWE2ZMQAUC/action/storage_attestation","attest_author":"https://pith.science/pith/IEEOFDJCIX665ZIYTWE2ZMQAUC/action/author_attestation","sign_citation":"https://pith.science/pith/IEEOFDJCIX665ZIYTWE2ZMQAUC/action/citation_signature","submit_replication":"https://pith.science/pith/IEEOFDJCIX665ZIYTWE2ZMQAUC/action/replication_record"}},"created_at":"2026-07-05T06:29:41.861861+00:00","updated_at":"2026-07-05T06:29:41.861861+00:00"}