{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:2WG55OCKP6ZPZZ6XDZWZVVOL4A","short_pith_number":"pith:2WG55OCK","schema_version":"1.0","canonical_sha256":"d58ddeb84a7fb2fce7d71e6d9ad5cbe031db74a448a10edb761054f6a289a8f3","source":{"kind":"arxiv","id":"2207.03546","version":1},"attestation_state":"computed","paper":{"title":"BibleTTS: a large, high-fidelity, multilingual, and uniquely African speech corpus","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Alp \\\"Oktem, Apelete Agbolo, Bernard Opoku, Chris Emezue, Colin Leong, Daniel Whitenack Julian Weber, David Ifeoluwa Adelani, Edresson Casanova, Elizabeth Salesky, Iroro Orife, Jesujoba Alabi, Jonathan Mukiibi, Josh Meyer, Perez Ogayo, Salomey Osei, Salomon Kabongo, Samuel Olanrewaju, Shamsuddeen Muhammad, Victor Akinode","submitted_at":"2022-07-07T19:35:43Z","abstract_excerpt":"BibleTTS is a large, high-quality, open speech dataset for ten languages spoken in Sub-Saharan Africa. The corpus contains up to 86 hours of aligned, studio quality 48kHz single speaker recordings per language, enabling the development of high-quality text-to-speech models. The ten languages represented are: Akuapem Twi, Asante Twi, Chichewa, Ewe, Hausa, Kikuyu, Lingala, Luganda, Luo, and Yoruba. This corpus is a derivative work of Bible recordings made and released by the Open.Bible project from Biblica. We have aligned, cleaned, and filtered the original recordings, and additionally hand-che"},"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":"2207.03546","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-07-07T19:35:43Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"c7bf58bf8328bc1625743a2e4c6beb2969c25a9dace19741f2a1bc1f0044f384","abstract_canon_sha256":"ac2cab6eeb5352181bb7b99873800bd9a0adf590641e8507f6261a95f7902c52"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:38:25.641719Z","signature_b64":"W8OxCpJ8ktS7RicWb43DdfCwDri8yXf8eoc91FkqTZEUEi8vCUePZaLLzkMqq2d1CVxKyTUhpD09APesV+4nAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d58ddeb84a7fb2fce7d71e6d9ad5cbe031db74a448a10edb761054f6a289a8f3","last_reissued_at":"2026-07-05T04:38:25.641265Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:38:25.641265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BibleTTS: a large, high-fidelity, multilingual, and uniquely African speech corpus","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Alp \\\"Oktem, Apelete Agbolo, Bernard Opoku, Chris Emezue, Colin Leong, Daniel Whitenack Julian Weber, David Ifeoluwa Adelani, Edresson Casanova, Elizabeth Salesky, Iroro Orife, Jesujoba Alabi, Jonathan Mukiibi, Josh Meyer, Perez Ogayo, Salomey Osei, Salomon Kabongo, Samuel Olanrewaju, Shamsuddeen Muhammad, Victor Akinode","submitted_at":"2022-07-07T19:35:43Z","abstract_excerpt":"BibleTTS is a large, high-quality, open speech dataset for ten languages spoken in Sub-Saharan Africa. The corpus contains up to 86 hours of aligned, studio quality 48kHz single speaker recordings per language, enabling the development of high-quality text-to-speech models. The ten languages represented are: Akuapem Twi, Asante Twi, Chichewa, Ewe, Hausa, Kikuyu, Lingala, Luganda, Luo, and Yoruba. This corpus is a derivative work of Bible recordings made and released by the Open.Bible project from Biblica. We have aligned, cleaned, and filtered the original recordings, and additionally hand-che"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.03546","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/2207.03546/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":"2207.03546","created_at":"2026-07-05T04:38:25.641329+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.03546v1","created_at":"2026-07-05T04:38:25.641329+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.03546","created_at":"2026-07-05T04:38:25.641329+00:00"},{"alias_kind":"pith_short_12","alias_value":"2WG55OCKP6ZP","created_at":"2026-07-05T04:38:25.641329+00:00"},{"alias_kind":"pith_short_16","alias_value":"2WG55OCKP6ZPZZ6X","created_at":"2026-07-05T04:38:25.641329+00:00"},{"alias_kind":"pith_short_8","alias_value":"2WG55OCK","created_at":"2026-07-05T04:38:25.641329+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/2WG55OCKP6ZPZZ6XDZWZVVOL4A","json":"https://pith.science/pith/2WG55OCKP6ZPZZ6XDZWZVVOL4A.json","graph_json":"https://pith.science/api/pith-number/2WG55OCKP6ZPZZ6XDZWZVVOL4A/graph.json","events_json":"https://pith.science/api/pith-number/2WG55OCKP6ZPZZ6XDZWZVVOL4A/events.json","paper":"https://pith.science/paper/2WG55OCK"},"agent_actions":{"view_html":"https://pith.science/pith/2WG55OCKP6ZPZZ6XDZWZVVOL4A","download_json":"https://pith.science/pith/2WG55OCKP6ZPZZ6XDZWZVVOL4A.json","view_paper":"https://pith.science/paper/2WG55OCK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.03546&json=true","fetch_graph":"https://pith.science/api/pith-number/2WG55OCKP6ZPZZ6XDZWZVVOL4A/graph.json","fetch_events":"https://pith.science/api/pith-number/2WG55OCKP6ZPZZ6XDZWZVVOL4A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2WG55OCKP6ZPZZ6XDZWZVVOL4A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2WG55OCKP6ZPZZ6XDZWZVVOL4A/action/storage_attestation","attest_author":"https://pith.science/pith/2WG55OCKP6ZPZZ6XDZWZVVOL4A/action/author_attestation","sign_citation":"https://pith.science/pith/2WG55OCKP6ZPZZ6XDZWZVVOL4A/action/citation_signature","submit_replication":"https://pith.science/pith/2WG55OCKP6ZPZZ6XDZWZVVOL4A/action/replication_record"}},"created_at":"2026-07-05T04:38:25.641329+00:00","updated_at":"2026-07-05T04:38:25.641329+00:00"}