{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:E5IUH2L3ABCI4ZBA74XULFXG57","short_pith_number":"pith:E5IUH2L3","schema_version":"1.0","canonical_sha256":"275143e97b00448e6420ff2f4596e6efec805f3ff8d324ae557650d6f09fe9f1","source":{"kind":"arxiv","id":"2502.14673","version":1},"attestation_state":"computed","paper":{"title":"ChunkFormer: Masked Chunking Conformer For Long-Form Speech Transcription","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Duc Thanh Chau, Dung Tran, Khanh Le, Tuan Vu Ho","submitted_at":"2025-02-20T16:06:06Z","abstract_excerpt":"Deploying ASR models at an industrial scale poses significant challenges in hardware resource management, especially for long-form transcription tasks where audio may last for hours. Large Conformer models, despite their capabilities, are limited to processing only 15 minutes of audio on an 80GB GPU. Furthermore, variable input lengths worsen inefficiencies, as standard batching leads to excessive padding, increasing resource consumption and execution time. To address this, we introduce ChunkFormer, an efficient ASR model that uses chunk-wise processing with relative right context, enabling lo"},"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":"2502.14673","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-02-20T16:06:06Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"46581443a3ea69d364ede1276c52c3083c89c4e4a8b0dc4e4f26bda337b0053e","abstract_canon_sha256":"790d529761d9af9027b418ee52dc92ea41067f192413bd5fce865a632d39d8b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:30.928696Z","signature_b64":"TyaR3p93OhmCXCXBu69nGWEqfBEtUDHuny0i7mApKpCtoWCU/6QwqofX3UPHa7Ne6hEFkSzPd/7bc9a9jCyTBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"275143e97b00448e6420ff2f4596e6efec805f3ff8d324ae557650d6f09fe9f1","last_reissued_at":"2026-07-05T10:17:30.928252Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:30.928252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ChunkFormer: Masked Chunking Conformer For Long-Form Speech Transcription","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Duc Thanh Chau, Dung Tran, Khanh Le, Tuan Vu Ho","submitted_at":"2025-02-20T16:06:06Z","abstract_excerpt":"Deploying ASR models at an industrial scale poses significant challenges in hardware resource management, especially for long-form transcription tasks where audio may last for hours. Large Conformer models, despite their capabilities, are limited to processing only 15 minutes of audio on an 80GB GPU. Furthermore, variable input lengths worsen inefficiencies, as standard batching leads to excessive padding, increasing resource consumption and execution time. To address this, we introduce ChunkFormer, an efficient ASR model that uses chunk-wise processing with relative right context, enabling lo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14673","kind":"arxiv","version":1},"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/2502.14673/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":"2502.14673","created_at":"2026-07-05T10:17:30.928310+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.14673v1","created_at":"2026-07-05T10:17:30.928310+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14673","created_at":"2026-07-05T10:17:30.928310+00:00"},{"alias_kind":"pith_short_12","alias_value":"E5IUH2L3ABCI","created_at":"2026-07-05T10:17:30.928310+00:00"},{"alias_kind":"pith_short_16","alias_value":"E5IUH2L3ABCI4ZBA","created_at":"2026-07-05T10:17:30.928310+00:00"},{"alias_kind":"pith_short_8","alias_value":"E5IUH2L3","created_at":"2026-07-05T10:17:30.928310+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E5IUH2L3ABCI4ZBA74XULFXG57","json":"https://pith.science/pith/E5IUH2L3ABCI4ZBA74XULFXG57.json","graph_json":"https://pith.science/api/pith-number/E5IUH2L3ABCI4ZBA74XULFXG57/graph.json","events_json":"https://pith.science/api/pith-number/E5IUH2L3ABCI4ZBA74XULFXG57/events.json","paper":"https://pith.science/paper/E5IUH2L3"},"agent_actions":{"view_html":"https://pith.science/pith/E5IUH2L3ABCI4ZBA74XULFXG57","download_json":"https://pith.science/pith/E5IUH2L3ABCI4ZBA74XULFXG57.json","view_paper":"https://pith.science/paper/E5IUH2L3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.14673&json=true","fetch_graph":"https://pith.science/api/pith-number/E5IUH2L3ABCI4ZBA74XULFXG57/graph.json","fetch_events":"https://pith.science/api/pith-number/E5IUH2L3ABCI4ZBA74XULFXG57/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E5IUH2L3ABCI4ZBA74XULFXG57/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E5IUH2L3ABCI4ZBA74XULFXG57/action/storage_attestation","attest_author":"https://pith.science/pith/E5IUH2L3ABCI4ZBA74XULFXG57/action/author_attestation","sign_citation":"https://pith.science/pith/E5IUH2L3ABCI4ZBA74XULFXG57/action/citation_signature","submit_replication":"https://pith.science/pith/E5IUH2L3ABCI4ZBA74XULFXG57/action/replication_record"}},"created_at":"2026-07-05T10:17:30.928310+00:00","updated_at":"2026-07-05T10:17:30.928310+00:00"}