{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:O6SPJ5VZE2NWOOL4DBJUUNFODL","short_pith_number":"pith:O6SPJ5VZ","schema_version":"1.0","canonical_sha256":"77a4f4f6b9269b67397c18534a34ae1adb5f730c4c46fc5907fedc8e3208aa84","source":{"kind":"arxiv","id":"2606.03504","version":1},"attestation_state":"computed","paper":{"title":"BaltiVoice: A Speech Corpus and Fine-tuned Whisper ASR System for the Balti Language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Muhammad Ali","submitted_at":"2026-06-02T11:23:49Z","abstract_excerpt":"We present BaltiVoice, a 16.8-hour read-speech corpus for Balti (ISO 639-3: bft), a Tibetic language spoken in Gilgit-Baltistan, Pakistan, with no prior publicly available ASR resources. The corpus contains 10,060 validated utterances in native Nastaliq script, derived from Mozilla Common Voice recordings. We fine-tune OpenAI Whisper-small on this corpus and report a Word Error Rate (WER) of 30.07% on a held-out validation set of 538 utterances, down from a measured zero-shot baseline of 182.18% for Whisper-small on Balti. The dataset, fine-tuned model, and a live transcription demo are public"},"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":"2606.03504","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T11:23:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6291b51f123418f9f477f4452621d854b3db91f76c6e8b547d2894f4581e6bd5","abstract_canon_sha256":"efcda8d389d5bda24055cf49c0f4f2ee89dafee28690483dad40bf68943edac9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:59.476365Z","signature_b64":"4rqM9RKAGu7GSDjGavnKNdjXVokWzVyU/zQgWgY1cs1wZqfVjHmrfoqUc5aoZ/8eXPZu1ZnZsGabEyIdrOlFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77a4f4f6b9269b67397c18534a34ae1adb5f730c4c46fc5907fedc8e3208aa84","last_reissued_at":"2026-06-03T01:05:59.475673Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:59.475673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BaltiVoice: A Speech Corpus and Fine-tuned Whisper ASR System for the Balti Language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Muhammad Ali","submitted_at":"2026-06-02T11:23:49Z","abstract_excerpt":"We present BaltiVoice, a 16.8-hour read-speech corpus for Balti (ISO 639-3: bft), a Tibetic language spoken in Gilgit-Baltistan, Pakistan, with no prior publicly available ASR resources. The corpus contains 10,060 validated utterances in native Nastaliq script, derived from Mozilla Common Voice recordings. We fine-tune OpenAI Whisper-small on this corpus and report a Word Error Rate (WER) of 30.07% on a held-out validation set of 538 utterances, down from a measured zero-shot baseline of 182.18% for Whisper-small on Balti. The dataset, fine-tuned model, and a live transcription demo are public"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03504","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/2606.03504/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":"2606.03504","created_at":"2026-06-03T01:05:59.475726+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.03504v1","created_at":"2026-06-03T01:05:59.475726+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03504","created_at":"2026-06-03T01:05:59.475726+00:00"},{"alias_kind":"pith_short_12","alias_value":"O6SPJ5VZE2NW","created_at":"2026-06-03T01:05:59.475726+00:00"},{"alias_kind":"pith_short_16","alias_value":"O6SPJ5VZE2NWOOL4","created_at":"2026-06-03T01:05:59.475726+00:00"},{"alias_kind":"pith_short_8","alias_value":"O6SPJ5VZ","created_at":"2026-06-03T01:05:59.475726+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/O6SPJ5VZE2NWOOL4DBJUUNFODL","json":"https://pith.science/pith/O6SPJ5VZE2NWOOL4DBJUUNFODL.json","graph_json":"https://pith.science/api/pith-number/O6SPJ5VZE2NWOOL4DBJUUNFODL/graph.json","events_json":"https://pith.science/api/pith-number/O6SPJ5VZE2NWOOL4DBJUUNFODL/events.json","paper":"https://pith.science/paper/O6SPJ5VZ"},"agent_actions":{"view_html":"https://pith.science/pith/O6SPJ5VZE2NWOOL4DBJUUNFODL","download_json":"https://pith.science/pith/O6SPJ5VZE2NWOOL4DBJUUNFODL.json","view_paper":"https://pith.science/paper/O6SPJ5VZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.03504&json=true","fetch_graph":"https://pith.science/api/pith-number/O6SPJ5VZE2NWOOL4DBJUUNFODL/graph.json","fetch_events":"https://pith.science/api/pith-number/O6SPJ5VZE2NWOOL4DBJUUNFODL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O6SPJ5VZE2NWOOL4DBJUUNFODL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O6SPJ5VZE2NWOOL4DBJUUNFODL/action/storage_attestation","attest_author":"https://pith.science/pith/O6SPJ5VZE2NWOOL4DBJUUNFODL/action/author_attestation","sign_citation":"https://pith.science/pith/O6SPJ5VZE2NWOOL4DBJUUNFODL/action/citation_signature","submit_replication":"https://pith.science/pith/O6SPJ5VZE2NWOOL4DBJUUNFODL/action/replication_record"}},"created_at":"2026-06-03T01:05:59.475726+00:00","updated_at":"2026-06-03T01:05:59.475726+00:00"}