{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RL26NM6T3NJWNYLLIXIIQEZLQU","short_pith_number":"pith:RL26NM6T","schema_version":"1.0","canonical_sha256":"8af5e6b3d3db5366e16b45d088132b850e09f4bed7633951c29375760a78f325","source":{"kind":"arxiv","id":"2507.10860","version":1},"attestation_state":"computed","paper":{"title":"WhisperKit: On-device Real-time ASR with Billion-Scale Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Arda Okan, Atila Orhon, Berkin Durmus, Eduardo Pacheco, Zach Nagengast","submitted_at":"2025-07-14T23:20:55Z","abstract_excerpt":"Real-time Automatic Speech Recognition (ASR) is a fundamental building block for many commercial applications of ML, including live captioning, dictation, meeting transcriptions, and medical scribes. Accuracy and latency are the most important factors when companies select a system to deploy. We present WhisperKit, an optimized on-device inference system for real-time ASR that significantly outperforms leading cloud-based systems. We benchmark against server-side systems that deploy a diverse set of models, including a frontier model (OpenAI gpt-4o-transcribe), a proprietary model (Deepgram no"},"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":"2507.10860","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-07-14T23:20:55Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"ed1526215c7d9b20b82b6186cfa41270fcbcfe5225a1eefbfbaec415cc99b662","abstract_canon_sha256":"a61549e24ae3380d60fdd26baffc86d13a919e92f8e4a018c9d34a16a6f68a06"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:37:27.139394Z","signature_b64":"PxyIo7vKGL9yVk3pGJs9aRmLTsE8x64FHe6UvdxTUVBTEOED3+QP/6Zp2SKBXC4TPp6hWGMHumVTE0Sv5s+zBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8af5e6b3d3db5366e16b45d088132b850e09f4bed7633951c29375760a78f325","last_reissued_at":"2026-07-05T11:37:27.138875Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:37:27.138875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WhisperKit: On-device Real-time ASR with Billion-Scale Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Arda Okan, Atila Orhon, Berkin Durmus, Eduardo Pacheco, Zach Nagengast","submitted_at":"2025-07-14T23:20:55Z","abstract_excerpt":"Real-time Automatic Speech Recognition (ASR) is a fundamental building block for many commercial applications of ML, including live captioning, dictation, meeting transcriptions, and medical scribes. Accuracy and latency are the most important factors when companies select a system to deploy. We present WhisperKit, an optimized on-device inference system for real-time ASR that significantly outperforms leading cloud-based systems. We benchmark against server-side systems that deploy a diverse set of models, including a frontier model (OpenAI gpt-4o-transcribe), a proprietary model (Deepgram no"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10860","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/2507.10860/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":"2507.10860","created_at":"2026-07-05T11:37:27.138938+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.10860v1","created_at":"2026-07-05T11:37:27.138938+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10860","created_at":"2026-07-05T11:37:27.138938+00:00"},{"alias_kind":"pith_short_12","alias_value":"RL26NM6T3NJW","created_at":"2026-07-05T11:37:27.138938+00:00"},{"alias_kind":"pith_short_16","alias_value":"RL26NM6T3NJWNYLL","created_at":"2026-07-05T11:37:27.138938+00:00"},{"alias_kind":"pith_short_8","alias_value":"RL26NM6T","created_at":"2026-07-05T11:37:27.138938+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/RL26NM6T3NJWNYLLIXIIQEZLQU","json":"https://pith.science/pith/RL26NM6T3NJWNYLLIXIIQEZLQU.json","graph_json":"https://pith.science/api/pith-number/RL26NM6T3NJWNYLLIXIIQEZLQU/graph.json","events_json":"https://pith.science/api/pith-number/RL26NM6T3NJWNYLLIXIIQEZLQU/events.json","paper":"https://pith.science/paper/RL26NM6T"},"agent_actions":{"view_html":"https://pith.science/pith/RL26NM6T3NJWNYLLIXIIQEZLQU","download_json":"https://pith.science/pith/RL26NM6T3NJWNYLLIXIIQEZLQU.json","view_paper":"https://pith.science/paper/RL26NM6T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.10860&json=true","fetch_graph":"https://pith.science/api/pith-number/RL26NM6T3NJWNYLLIXIIQEZLQU/graph.json","fetch_events":"https://pith.science/api/pith-number/RL26NM6T3NJWNYLLIXIIQEZLQU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RL26NM6T3NJWNYLLIXIIQEZLQU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RL26NM6T3NJWNYLLIXIIQEZLQU/action/storage_attestation","attest_author":"https://pith.science/pith/RL26NM6T3NJWNYLLIXIIQEZLQU/action/author_attestation","sign_citation":"https://pith.science/pith/RL26NM6T3NJWNYLLIXIIQEZLQU/action/citation_signature","submit_replication":"https://pith.science/pith/RL26NM6T3NJWNYLLIXIIQEZLQU/action/replication_record"}},"created_at":"2026-07-05T11:37:27.138938+00:00","updated_at":"2026-07-05T11:37:27.138938+00:00"}