{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:COUZ4WUOUI2MRO3EJITZN5LWZD","short_pith_number":"pith:COUZ4WUO","schema_version":"1.0","canonical_sha256":"13a99e5a8ea234c8bb644a2796f576c8d603e9d835074e6d24ddc8a86f9867cf","source":{"kind":"arxiv","id":"2607.17164","version":1},"attestation_state":"computed","paper":{"title":"Robust Assamese Speech Recognition through Controlled Fine-Tuning of Whisper Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dwipen Laskar, Ganapati Das, Hasin Afzal Ahmed, Hem Chandra Das, Kshirod Sarmah, Manjula Kalita, Sanjib Kr Kalita","submitted_at":"2026-07-19T09:54:52Z","abstract_excerpt":"Developing Automatic Speech Recognition (ASR) for morphologically rich, low-resource languages such as Assamese is challenging due to insufficient annotated speech data. The pretrained Whisper model performs poorly on Assamese speech recognition tasks. This paper presents a controlled, fine-tuned Whisper-based Assamese ASR system trained on the Mozilla Common Voice 24.0-Assamese corpus. A hardware-aware optimized training pipeline is implemented for resource-constrained environments, employing mixed-precision training and gradient accumulation on Tesla 4 Graphics Processing Units (T4 GPUs). Th"},"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":"2607.17164","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-19T09:54:52Z","cross_cats_sorted":[],"title_canon_sha256":"6d095eed4bff9a9671736115131fa7e0c5f50571b01093fcca40eddac2e6bc80","abstract_canon_sha256":"9df3594b9c2c5e8f48e55701ba83558b4e2103a8d010467820836627800ce086"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T01:21:18.833823Z","signature_b64":"HVgou4WqQ34F99MCONFJKNEmBkdcyGnLPVLdbYRhHCN7JBY0RKp54Lp7ESn+LJI4TqDfWAYx2rbYtOOgYg+yBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13a99e5a8ea234c8bb644a2796f576c8d603e9d835074e6d24ddc8a86f9867cf","last_reissued_at":"2026-07-21T01:21:18.832838Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T01:21:18.832838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Assamese Speech Recognition through Controlled Fine-Tuning of Whisper Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dwipen Laskar, Ganapati Das, Hasin Afzal Ahmed, Hem Chandra Das, Kshirod Sarmah, Manjula Kalita, Sanjib Kr Kalita","submitted_at":"2026-07-19T09:54:52Z","abstract_excerpt":"Developing Automatic Speech Recognition (ASR) for morphologically rich, low-resource languages such as Assamese is challenging due to insufficient annotated speech data. The pretrained Whisper model performs poorly on Assamese speech recognition tasks. This paper presents a controlled, fine-tuned Whisper-based Assamese ASR system trained on the Mozilla Common Voice 24.0-Assamese corpus. A hardware-aware optimized training pipeline is implemented for resource-constrained environments, employing mixed-precision training and gradient accumulation on Tesla 4 Graphics Processing Units (T4 GPUs). Th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.17164","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/2607.17164/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":"2607.17164","created_at":"2026-07-21T01:21:18.833300+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.17164v1","created_at":"2026-07-21T01:21:18.833300+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.17164","created_at":"2026-07-21T01:21:18.833300+00:00"},{"alias_kind":"pith_short_12","alias_value":"COUZ4WUOUI2M","created_at":"2026-07-21T01:21:18.833300+00:00"},{"alias_kind":"pith_short_16","alias_value":"COUZ4WUOUI2MRO3E","created_at":"2026-07-21T01:21:18.833300+00:00"},{"alias_kind":"pith_short_8","alias_value":"COUZ4WUO","created_at":"2026-07-21T01:21:18.833300+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/COUZ4WUOUI2MRO3EJITZN5LWZD","json":"https://pith.science/pith/COUZ4WUOUI2MRO3EJITZN5LWZD.json","graph_json":"https://pith.science/api/pith-number/COUZ4WUOUI2MRO3EJITZN5LWZD/graph.json","events_json":"https://pith.science/api/pith-number/COUZ4WUOUI2MRO3EJITZN5LWZD/events.json","paper":"https://pith.science/paper/COUZ4WUO"},"agent_actions":{"view_html":"https://pith.science/pith/COUZ4WUOUI2MRO3EJITZN5LWZD","download_json":"https://pith.science/pith/COUZ4WUOUI2MRO3EJITZN5LWZD.json","view_paper":"https://pith.science/paper/COUZ4WUO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.17164&json=true","fetch_graph":"https://pith.science/api/pith-number/COUZ4WUOUI2MRO3EJITZN5LWZD/graph.json","fetch_events":"https://pith.science/api/pith-number/COUZ4WUOUI2MRO3EJITZN5LWZD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/COUZ4WUOUI2MRO3EJITZN5LWZD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/COUZ4WUOUI2MRO3EJITZN5LWZD/action/storage_attestation","attest_author":"https://pith.science/pith/COUZ4WUOUI2MRO3EJITZN5LWZD/action/author_attestation","sign_citation":"https://pith.science/pith/COUZ4WUOUI2MRO3EJITZN5LWZD/action/citation_signature","submit_replication":"https://pith.science/pith/COUZ4WUOUI2MRO3EJITZN5LWZD/action/replication_record"}},"created_at":"2026-07-21T01:21:18.833300+00:00","updated_at":"2026-07-21T01:21:18.833300+00:00"}