{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IWRF3EOCIEQY3KPYLQR7K7ECNQ","short_pith_number":"pith:IWRF3EOC","schema_version":"1.0","canonical_sha256":"45a25d91c241218da9f85c23f57c826c0a9d7226bc4efa4c1db36cb7dd11606d","source":{"kind":"arxiv","id":"2409.07259","version":1},"attestation_state":"computed","paper":{"title":"ManaTTS Persian: a recipe for creating TTS datasets for lower resource languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Hamid R. Rabiee, Mahta Fetrat Qharabagh, Zahra Dehghanian","submitted_at":"2024-09-11T13:28:41Z","abstract_excerpt":"In this study, we introduce ManaTTS, the most extensive publicly accessible single-speaker Persian corpus, and a comprehensive framework for collecting transcribed speech datasets for the Persian language. ManaTTS, released under the open CC-0 license, comprises approximately 86 hours of audio with a sampling rate of 44.1 kHz. Alongside ManaTTS, we also generated the VirgoolInformal dataset to evaluate Persian speech recognition models used for forced alignment, extending over 5 hours of audio. The datasets are supported by a fully transparent, MIT-licensed pipeline, a testament to innovation "},"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":"2409.07259","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-11T13:28:41Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"23172a1b273ef2db6f6bf3960a32c93ca3e936a8a0f130ab2c1aa92bd101d2e9","abstract_canon_sha256":"0b0d619f1fca3f4ee7ec7eba4addc116ac2efd3c58a908c3b29f1bad6e301245"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:05:47.938290Z","signature_b64":"X2guGqrTBN6syPHCmWTIOBZ1zEUeKHBHXQCX+6Zvh+LFlgPYT7ZAeBpmS/TldhyxRpNsWSraaghXCUMf1H4zDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45a25d91c241218da9f85c23f57c826c0a9d7226bc4efa4c1db36cb7dd11606d","last_reissued_at":"2026-07-05T09:05:47.937808Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:05:47.937808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ManaTTS Persian: a recipe for creating TTS datasets for lower resource languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Hamid R. Rabiee, Mahta Fetrat Qharabagh, Zahra Dehghanian","submitted_at":"2024-09-11T13:28:41Z","abstract_excerpt":"In this study, we introduce ManaTTS, the most extensive publicly accessible single-speaker Persian corpus, and a comprehensive framework for collecting transcribed speech datasets for the Persian language. ManaTTS, released under the open CC-0 license, comprises approximately 86 hours of audio with a sampling rate of 44.1 kHz. Alongside ManaTTS, we also generated the VirgoolInformal dataset to evaluate Persian speech recognition models used for forced alignment, extending over 5 hours of audio. The datasets are supported by a fully transparent, MIT-licensed pipeline, a testament to innovation "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.07259","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/2409.07259/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":"2409.07259","created_at":"2026-07-05T09:05:47.937867+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.07259v1","created_at":"2026-07-05T09:05:47.937867+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.07259","created_at":"2026-07-05T09:05:47.937867+00:00"},{"alias_kind":"pith_short_12","alias_value":"IWRF3EOCIEQY","created_at":"2026-07-05T09:05:47.937867+00:00"},{"alias_kind":"pith_short_16","alias_value":"IWRF3EOCIEQY3KPY","created_at":"2026-07-05T09:05:47.937867+00:00"},{"alias_kind":"pith_short_8","alias_value":"IWRF3EOC","created_at":"2026-07-05T09:05:47.937867+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/IWRF3EOCIEQY3KPYLQR7K7ECNQ","json":"https://pith.science/pith/IWRF3EOCIEQY3KPYLQR7K7ECNQ.json","graph_json":"https://pith.science/api/pith-number/IWRF3EOCIEQY3KPYLQR7K7ECNQ/graph.json","events_json":"https://pith.science/api/pith-number/IWRF3EOCIEQY3KPYLQR7K7ECNQ/events.json","paper":"https://pith.science/paper/IWRF3EOC"},"agent_actions":{"view_html":"https://pith.science/pith/IWRF3EOCIEQY3KPYLQR7K7ECNQ","download_json":"https://pith.science/pith/IWRF3EOCIEQY3KPYLQR7K7ECNQ.json","view_paper":"https://pith.science/paper/IWRF3EOC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.07259&json=true","fetch_graph":"https://pith.science/api/pith-number/IWRF3EOCIEQY3KPYLQR7K7ECNQ/graph.json","fetch_events":"https://pith.science/api/pith-number/IWRF3EOCIEQY3KPYLQR7K7ECNQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IWRF3EOCIEQY3KPYLQR7K7ECNQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IWRF3EOCIEQY3KPYLQR7K7ECNQ/action/storage_attestation","attest_author":"https://pith.science/pith/IWRF3EOCIEQY3KPYLQR7K7ECNQ/action/author_attestation","sign_citation":"https://pith.science/pith/IWRF3EOCIEQY3KPYLQR7K7ECNQ/action/citation_signature","submit_replication":"https://pith.science/pith/IWRF3EOCIEQY3KPYLQR7K7ECNQ/action/replication_record"}},"created_at":"2026-07-05T09:05:47.937867+00:00","updated_at":"2026-07-05T09:05:47.937867+00:00"}