{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DFCVVV2PAZ3MNH6S6NKEHFYDMW","short_pith_number":"pith:DFCVVV2P","schema_version":"1.0","canonical_sha256":"19455ad74f0676c69fd2f35443970365b380f7588495020dd7606bb82f39df9c","source":{"kind":"arxiv","id":"2607.21540","version":1},"attestation_state":"computed","paper":{"title":"DONDO: Open w2v-BERT Speech-Recognition Base Models for African Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Paul Azunre","submitted_at":"2026-07-23T17:25:08Z","abstract_excerpt":"We present DONDO, a family of open, permissively licensed automatic speech recognition (ASR) base models for African languages, built on the w2v-BERT 2.0 self-supervised speech encoder. DONDO comprises twenty-one monolingual models and five multilingual models spanning twenty-seven language varieties across Ghana, Sierra Leone, Nigeria, Senegal, Kenya and Zimbabwe. Models are fine-tuned primarily on read speech drawn from religious texts, which offer broad, license-clear and orthographically consistent coverage for languages that otherwise lack transcribed audio. We describe a two-step (and, f"},"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":"2607.21540","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-23T17:25:08Z","cross_cats_sorted":[],"title_canon_sha256":"fb326466f3ce1f1103397c1b2a9781382fb81a8c5166e592cc1994c59377e62d","abstract_canon_sha256":"7a8509a30bd3d5a8dadb881b3bdbcb1e0d4047925839720570707fbb2cdcf44c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-24T01:24:38.466111Z","signature_b64":"uLVY8accPMpARFt5p5V3z4XaKiPTdqus4J5Mrv/+W4TMc0DKuLXJtC5nSa+GsFFQgU8JCt1mIr0nvyXSHnQeBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19455ad74f0676c69fd2f35443970365b380f7588495020dd7606bb82f39df9c","last_reissued_at":"2026-07-24T01:24:38.465253Z","signature_status":"signed_v1","first_computed_at":"2026-07-24T01:24:38.465253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DONDO: Open w2v-BERT Speech-Recognition Base Models for African Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Paul Azunre","submitted_at":"2026-07-23T17:25:08Z","abstract_excerpt":"We present DONDO, a family of open, permissively licensed automatic speech recognition (ASR) base models for African languages, built on the w2v-BERT 2.0 self-supervised speech encoder. DONDO comprises twenty-one monolingual models and five multilingual models spanning twenty-seven language varieties across Ghana, Sierra Leone, Nigeria, Senegal, Kenya and Zimbabwe. Models are fine-tuned primarily on read speech drawn from religious texts, which offer broad, license-clear and orthographically consistent coverage for languages that otherwise lack transcribed audio. We describe a two-step (and, f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21540","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/2607.21540/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":"2607.21540","created_at":"2026-07-24T01:24:38.465693+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.21540v1","created_at":"2026-07-24T01:24:38.465693+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21540","created_at":"2026-07-24T01:24:38.465693+00:00"},{"alias_kind":"pith_short_12","alias_value":"DFCVVV2PAZ3M","created_at":"2026-07-24T01:24:38.465693+00:00"},{"alias_kind":"pith_short_16","alias_value":"DFCVVV2PAZ3MNH6S","created_at":"2026-07-24T01:24:38.465693+00:00"},{"alias_kind":"pith_short_8","alias_value":"DFCVVV2P","created_at":"2026-07-24T01:24:38.465693+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/DFCVVV2PAZ3MNH6S6NKEHFYDMW","json":"https://pith.science/pith/DFCVVV2PAZ3MNH6S6NKEHFYDMW.json","graph_json":"https://pith.science/api/pith-number/DFCVVV2PAZ3MNH6S6NKEHFYDMW/graph.json","events_json":"https://pith.science/api/pith-number/DFCVVV2PAZ3MNH6S6NKEHFYDMW/events.json","paper":"https://pith.science/paper/DFCVVV2P"},"agent_actions":{"view_html":"https://pith.science/pith/DFCVVV2PAZ3MNH6S6NKEHFYDMW","download_json":"https://pith.science/pith/DFCVVV2PAZ3MNH6S6NKEHFYDMW.json","view_paper":"https://pith.science/paper/DFCVVV2P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.21540&json=true","fetch_graph":"https://pith.science/api/pith-number/DFCVVV2PAZ3MNH6S6NKEHFYDMW/graph.json","fetch_events":"https://pith.science/api/pith-number/DFCVVV2PAZ3MNH6S6NKEHFYDMW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DFCVVV2PAZ3MNH6S6NKEHFYDMW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DFCVVV2PAZ3MNH6S6NKEHFYDMW/action/storage_attestation","attest_author":"https://pith.science/pith/DFCVVV2PAZ3MNH6S6NKEHFYDMW/action/author_attestation","sign_citation":"https://pith.science/pith/DFCVVV2PAZ3MNH6S6NKEHFYDMW/action/citation_signature","submit_replication":"https://pith.science/pith/DFCVVV2PAZ3MNH6S6NKEHFYDMW/action/replication_record"}},"created_at":"2026-07-24T01:24:38.465693+00:00","updated_at":"2026-07-24T01:24:38.465693+00:00"}