{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IWMOV5MTKGUQ4B2WMMXMWHUD4S","short_pith_number":"pith:IWMOV5MT","schema_version":"1.0","canonical_sha256":"4598eaf59351a90e0756632ecb1e83e4a017c3fb2d7c646a7b67a1438f938273","source":{"kind":"arxiv","id":"2507.14451","version":1},"attestation_state":"computed","paper":{"title":"Adapting Whisper for Lightweight and Efficient Automatic Speech Recognition of Children for On-device Edge Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC","cs.SD"],"primary_cat":"eess.AS","authors_text":"John Hansen, Satwik Dutta, Shruthigna Chandupatla","submitted_at":"2025-07-19T02:55:48Z","abstract_excerpt":"Reliability on cloud providers for ASR inference to support child-centered voice-based applications is becoming challenging due to regulatory and privacy challenges. Motivated by a privacy-preserving design, this study aims to develop a lightweight & efficient Whisper ASR system capable of running on a Raspberry Pi. Upon evaluation of the MyST corpus and by examining various filtering strategies to fine-tune the `tiny.en' model, a Word Error Rate (WER) of 15.9% was achieved (11.8% filtered). A low-rank compression reduces the encoder size by 0.51M with 1.26x faster inference in GPU, with 11% r"},"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":"2507.14451","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-07-19T02:55:48Z","cross_cats_sorted":["cs.HC","cs.SD"],"title_canon_sha256":"f1d648b63111586cc81a52382786b6ad02879b8be08867343d173951ec8e4f18","abstract_canon_sha256":"48a6167d316789f7a174ae6e3820dec40369ee6b749ca3450a7244fa3647d3e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:07.380635Z","signature_b64":"CS6+YnqBxLzw4QX7ay8LZbdTVde7AB+IjpSLiieBzziJ6yrk2mrnByfHxMUX82ITQn+QJ5ZABYJOGlTr1eReCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4598eaf59351a90e0756632ecb1e83e4a017c3fb2d7c646a7b67a1438f938273","last_reissued_at":"2026-07-05T11:40:07.380134Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:07.380134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adapting Whisper for Lightweight and Efficient Automatic Speech Recognition of Children for On-device Edge Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC","cs.SD"],"primary_cat":"eess.AS","authors_text":"John Hansen, Satwik Dutta, Shruthigna Chandupatla","submitted_at":"2025-07-19T02:55:48Z","abstract_excerpt":"Reliability on cloud providers for ASR inference to support child-centered voice-based applications is becoming challenging due to regulatory and privacy challenges. Motivated by a privacy-preserving design, this study aims to develop a lightweight & efficient Whisper ASR system capable of running on a Raspberry Pi. Upon evaluation of the MyST corpus and by examining various filtering strategies to fine-tune the `tiny.en' model, a Word Error Rate (WER) of 15.9% was achieved (11.8% filtered). A low-rank compression reduces the encoder size by 0.51M with 1.26x faster inference in GPU, with 11% r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.14451","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/2507.14451/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":"2507.14451","created_at":"2026-07-05T11:40:07.380201+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.14451v1","created_at":"2026-07-05T11:40:07.380201+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.14451","created_at":"2026-07-05T11:40:07.380201+00:00"},{"alias_kind":"pith_short_12","alias_value":"IWMOV5MTKGUQ","created_at":"2026-07-05T11:40:07.380201+00:00"},{"alias_kind":"pith_short_16","alias_value":"IWMOV5MTKGUQ4B2W","created_at":"2026-07-05T11:40:07.380201+00:00"},{"alias_kind":"pith_short_8","alias_value":"IWMOV5MT","created_at":"2026-07-05T11:40:07.380201+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.14451","citing_title":"Adapting Whisper for Lightweight and Efficient Automatic Speech Recognition of Children for On-device Edge Applications","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IWMOV5MTKGUQ4B2WMMXMWHUD4S","json":"https://pith.science/pith/IWMOV5MTKGUQ4B2WMMXMWHUD4S.json","graph_json":"https://pith.science/api/pith-number/IWMOV5MTKGUQ4B2WMMXMWHUD4S/graph.json","events_json":"https://pith.science/api/pith-number/IWMOV5MTKGUQ4B2WMMXMWHUD4S/events.json","paper":"https://pith.science/paper/IWMOV5MT"},"agent_actions":{"view_html":"https://pith.science/pith/IWMOV5MTKGUQ4B2WMMXMWHUD4S","download_json":"https://pith.science/pith/IWMOV5MTKGUQ4B2WMMXMWHUD4S.json","view_paper":"https://pith.science/paper/IWMOV5MT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.14451&json=true","fetch_graph":"https://pith.science/api/pith-number/IWMOV5MTKGUQ4B2WMMXMWHUD4S/graph.json","fetch_events":"https://pith.science/api/pith-number/IWMOV5MTKGUQ4B2WMMXMWHUD4S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IWMOV5MTKGUQ4B2WMMXMWHUD4S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IWMOV5MTKGUQ4B2WMMXMWHUD4S/action/storage_attestation","attest_author":"https://pith.science/pith/IWMOV5MTKGUQ4B2WMMXMWHUD4S/action/author_attestation","sign_citation":"https://pith.science/pith/IWMOV5MTKGUQ4B2WMMXMWHUD4S/action/citation_signature","submit_replication":"https://pith.science/pith/IWMOV5MTKGUQ4B2WMMXMWHUD4S/action/replication_record"}},"created_at":"2026-07-05T11:40:07.380201+00:00","updated_at":"2026-07-05T11:40:07.380201+00:00"}