{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KNQ4ODRRX5UE2UUURZJXDSUV4M","short_pith_number":"pith:KNQ4ODRR","schema_version":"1.0","canonical_sha256":"5361c70e31bf684d52948e5371ca95e30b9a03dfee98f9e0e2eb2869e114bb2c","source":{"kind":"arxiv","id":"2412.10705","version":1},"attestation_state":"computed","paper":{"title":"Efficient Adaptation of Multilingual Models for Japanese ASR","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Haruka Fukukawa, Mark Bajo, Ryuji Morita, Yuma Ogasawara","submitted_at":"2024-12-14T06:32:16Z","abstract_excerpt":"This study explores fine-tuning multilingual ASR (Automatic Speech Recognition) models, specifically OpenAI's Whisper-Tiny, to improve performance in Japanese. While multilingual models like Whisper offer versatility, they often lack precision in specific languages. Conversely, monolingual models like ReazonSpeech excel in language-specific tasks but are less adaptable. Using Japanese-specific datasets and Low-Rank Adaptation (LoRA) along with end-to-end (E2E) training, we fine-tuned Whisper-Tiny to bridge this gap. Our results show that fine-tuning reduced Whisper-Tiny's Character Error Rate "},"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":"2412.10705","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-14T06:32:16Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"6bb777b6f44f18c348481ed8303bf2925a5714ba8371be4cadb7b9f6d898117f","abstract_canon_sha256":"a177391f8ce5df3060c6efd93ffe40a02b74e1ecdaf8f776b3066a5f6ed84d6d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:20.095818Z","signature_b64":"O4hqc1l/VvW6doLZaI7QjCHmERxnkuSVeFTS7VCA7usBDEySrvV237HNT/yL6xCYA5Q46wmdEnkGhRpamMogAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5361c70e31bf684d52948e5371ca95e30b9a03dfee98f9e0e2eb2869e114bb2c","last_reissued_at":"2026-07-05T09:49:20.094580Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:20.094580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Adaptation of Multilingual Models for Japanese ASR","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Haruka Fukukawa, Mark Bajo, Ryuji Morita, Yuma Ogasawara","submitted_at":"2024-12-14T06:32:16Z","abstract_excerpt":"This study explores fine-tuning multilingual ASR (Automatic Speech Recognition) models, specifically OpenAI's Whisper-Tiny, to improve performance in Japanese. While multilingual models like Whisper offer versatility, they often lack precision in specific languages. Conversely, monolingual models like ReazonSpeech excel in language-specific tasks but are less adaptable. Using Japanese-specific datasets and Low-Rank Adaptation (LoRA) along with end-to-end (E2E) training, we fine-tuned Whisper-Tiny to bridge this gap. Our results show that fine-tuning reduced Whisper-Tiny's Character Error Rate "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10705","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/2412.10705/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":"2412.10705","created_at":"2026-07-05T09:49:20.095430+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.10705v1","created_at":"2026-07-05T09:49:20.095430+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10705","created_at":"2026-07-05T09:49:20.095430+00:00"},{"alias_kind":"pith_short_12","alias_value":"KNQ4ODRRX5UE","created_at":"2026-07-05T09:49:20.095430+00:00"},{"alias_kind":"pith_short_16","alias_value":"KNQ4ODRRX5UE2UUU","created_at":"2026-07-05T09:49:20.095430+00:00"},{"alias_kind":"pith_short_8","alias_value":"KNQ4ODRR","created_at":"2026-07-05T09:49:20.095430+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.11130","citing_title":"A Self-Refining Framework for Enhancing ASR Using TTS-Synthesized Data","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KNQ4ODRRX5UE2UUURZJXDSUV4M","json":"https://pith.science/pith/KNQ4ODRRX5UE2UUURZJXDSUV4M.json","graph_json":"https://pith.science/api/pith-number/KNQ4ODRRX5UE2UUURZJXDSUV4M/graph.json","events_json":"https://pith.science/api/pith-number/KNQ4ODRRX5UE2UUURZJXDSUV4M/events.json","paper":"https://pith.science/paper/KNQ4ODRR"},"agent_actions":{"view_html":"https://pith.science/pith/KNQ4ODRRX5UE2UUURZJXDSUV4M","download_json":"https://pith.science/pith/KNQ4ODRRX5UE2UUURZJXDSUV4M.json","view_paper":"https://pith.science/paper/KNQ4ODRR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.10705&json=true","fetch_graph":"https://pith.science/api/pith-number/KNQ4ODRRX5UE2UUURZJXDSUV4M/graph.json","fetch_events":"https://pith.science/api/pith-number/KNQ4ODRRX5UE2UUURZJXDSUV4M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KNQ4ODRRX5UE2UUURZJXDSUV4M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KNQ4ODRRX5UE2UUURZJXDSUV4M/action/storage_attestation","attest_author":"https://pith.science/pith/KNQ4ODRRX5UE2UUURZJXDSUV4M/action/author_attestation","sign_citation":"https://pith.science/pith/KNQ4ODRRX5UE2UUURZJXDSUV4M/action/citation_signature","submit_replication":"https://pith.science/pith/KNQ4ODRRX5UE2UUURZJXDSUV4M/action/replication_record"}},"created_at":"2026-07-05T09:49:20.095430+00:00","updated_at":"2026-07-05T09:49:20.095430+00:00"}