{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:H7YU722LIKBF2SBWPMDV2WFVMN","short_pith_number":"pith:H7YU722L","schema_version":"1.0","canonical_sha256":"3ff14feb4b42825d48367b075d58b56356005c1ebb0e9bfdad867196ef30d922","source":{"kind":"arxiv","id":"2305.10788","version":2},"attestation_state":"computed","paper":{"title":"DQ-Whisper: Joint Distillation and Quantization for Efficient Multilingual Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bei Liu, Hang Shao, Wei Wang, Xun Gong, Yanmin Qian","submitted_at":"2023-05-18T08:00:09Z","abstract_excerpt":"As a popular multilingual and multitask pre-trained speech model, Whisper has the problem of curse of multilinguality. To enhance multilingual capabilities in small Whisper models, we propose DQ-Whisper, a novel joint distillation and quantization framework to compress Whisper for efficient inference. Firstly, we propose a novel dynamic matching distillation strategy. Then, a quantization-aware distillation framework is introduced to integrate quantization with distillation. Experimental results on various multilingual datasets show that our suggested distillation approach can effectively enha"},"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":"2305.10788","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-05-18T08:00:09Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"e97b9b7e9e3b48bbb97524d8a76c21942cc6e3807a80c5c61609f4602b11fed0","abstract_canon_sha256":"751ebf26a8599a3f6a6d754f91866b3e87e118699d3abfca532972f0a8db8d02"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:12:53.089699Z","signature_b64":"2Ct7CcLFg810h+gOgkZPP1LBbTo/oJfMix0Qt9BqADqNeW4dx5630AwDU0y7GJarUNio2EOUF1P5I+pkTsOlBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ff14feb4b42825d48367b075d58b56356005c1ebb0e9bfdad867196ef30d922","last_reissued_at":"2026-07-05T09:12:53.089134Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:12:53.089134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DQ-Whisper: Joint Distillation and Quantization for Efficient Multilingual Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bei Liu, Hang Shao, Wei Wang, Xun Gong, Yanmin Qian","submitted_at":"2023-05-18T08:00:09Z","abstract_excerpt":"As a popular multilingual and multitask pre-trained speech model, Whisper has the problem of curse of multilinguality. To enhance multilingual capabilities in small Whisper models, we propose DQ-Whisper, a novel joint distillation and quantization framework to compress Whisper for efficient inference. Firstly, we propose a novel dynamic matching distillation strategy. Then, a quantization-aware distillation framework is introduced to integrate quantization with distillation. Experimental results on various multilingual datasets show that our suggested distillation approach can effectively enha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10788","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/2305.10788/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":"2305.10788","created_at":"2026-07-05T09:12:53.089207+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.10788v2","created_at":"2026-07-05T09:12:53.089207+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10788","created_at":"2026-07-05T09:12:53.089207+00:00"},{"alias_kind":"pith_short_12","alias_value":"H7YU722LIKBF","created_at":"2026-07-05T09:12:53.089207+00:00"},{"alias_kind":"pith_short_16","alias_value":"H7YU722LIKBF2SBW","created_at":"2026-07-05T09:12:53.089207+00:00"},{"alias_kind":"pith_short_8","alias_value":"H7YU722L","created_at":"2026-07-05T09:12:53.089207+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.03722","citing_title":"MFLA: Monotonic Finite Look-ahead Attention for Streaming Speech Recognition","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H7YU722LIKBF2SBWPMDV2WFVMN","json":"https://pith.science/pith/H7YU722LIKBF2SBWPMDV2WFVMN.json","graph_json":"https://pith.science/api/pith-number/H7YU722LIKBF2SBWPMDV2WFVMN/graph.json","events_json":"https://pith.science/api/pith-number/H7YU722LIKBF2SBWPMDV2WFVMN/events.json","paper":"https://pith.science/paper/H7YU722L"},"agent_actions":{"view_html":"https://pith.science/pith/H7YU722LIKBF2SBWPMDV2WFVMN","download_json":"https://pith.science/pith/H7YU722LIKBF2SBWPMDV2WFVMN.json","view_paper":"https://pith.science/paper/H7YU722L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.10788&json=true","fetch_graph":"https://pith.science/api/pith-number/H7YU722LIKBF2SBWPMDV2WFVMN/graph.json","fetch_events":"https://pith.science/api/pith-number/H7YU722LIKBF2SBWPMDV2WFVMN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H7YU722LIKBF2SBWPMDV2WFVMN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H7YU722LIKBF2SBWPMDV2WFVMN/action/storage_attestation","attest_author":"https://pith.science/pith/H7YU722LIKBF2SBWPMDV2WFVMN/action/author_attestation","sign_citation":"https://pith.science/pith/H7YU722LIKBF2SBWPMDV2WFVMN/action/citation_signature","submit_replication":"https://pith.science/pith/H7YU722LIKBF2SBWPMDV2WFVMN/action/replication_record"}},"created_at":"2026-07-05T09:12:53.089207+00:00","updated_at":"2026-07-05T09:12:53.089207+00:00"}