{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:NYGUT64WM7K7M5ODH7ILZEIPZF","short_pith_number":"pith:NYGUT64W","schema_version":"1.0","canonical_sha256":"6e0d49fb9667d5f675c33fd0bc910fc964f4abe2b4ce2762080b5154509a99c2","source":{"kind":"arxiv","id":"2010.05171","version":2},"attestation_state":"computed","paper":{"title":"fairseq S2T: Fast Speech-to-Text Modeling with fairseq","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Anne Wu, Changhan Wang, Dmytro Okhonko, Juan Pino, Sravya Popuri, Xutai Ma, Yun Tang","submitted_at":"2020-10-11T05:36:54Z","abstract_excerpt":"We introduce fairseq S2T, a fairseq extension for speech-to-text (S2T) modeling tasks such as end-to-end speech recognition and speech-to-text translation. It follows fairseq's careful design for scalability and extensibility. We provide end-to-end workflows from data pre-processing, model training to offline (online) inference. We implement state-of-the-art RNN-based, Transformer-based as well as Conformer-based models and open-source detailed training recipes. Fairseq's machine translation models and language models can be seamlessly integrated into S2T workflows for multi-task learning or t"},"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":"2010.05171","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-11T05:36:54Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"b05c2df756506b9232d7f34400354c76ec18899f313f9c45abdd79b51a6ee5f3","abstract_canon_sha256":"c23c0d9b5bd42a75ef38fc43ad27ac827d29f3f68eb47806e398d0649c4ed18e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:31:20.183689Z","signature_b64":"XsZRJZ0O4DHGOX7QQhtUaQC5aGSsHA9aZp6dNVGKsEuxO2drebDH7w5db4a/+ynpECjXVWMjXeY7J7U2/KnaCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e0d49fb9667d5f675c33fd0bc910fc964f4abe2b4ce2762080b5154509a99c2","last_reissued_at":"2026-07-05T04:31:20.183251Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:31:20.183251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"fairseq S2T: Fast Speech-to-Text Modeling with fairseq","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Anne Wu, Changhan Wang, Dmytro Okhonko, Juan Pino, Sravya Popuri, Xutai Ma, Yun Tang","submitted_at":"2020-10-11T05:36:54Z","abstract_excerpt":"We introduce fairseq S2T, a fairseq extension for speech-to-text (S2T) modeling tasks such as end-to-end speech recognition and speech-to-text translation. It follows fairseq's careful design for scalability and extensibility. We provide end-to-end workflows from data pre-processing, model training to offline (online) inference. We implement state-of-the-art RNN-based, Transformer-based as well as Conformer-based models and open-source detailed training recipes. Fairseq's machine translation models and language models can be seamlessly integrated into S2T workflows for multi-task learning or t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.05171","kind":"arxiv","version":2},"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/2010.05171/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":"2010.05171","created_at":"2026-07-05T04:31:20.183309+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.05171v2","created_at":"2026-07-05T04:31:20.183309+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.05171","created_at":"2026-07-05T04:31:20.183309+00:00"},{"alias_kind":"pith_short_12","alias_value":"NYGUT64WM7K7","created_at":"2026-07-05T04:31:20.183309+00:00"},{"alias_kind":"pith_short_16","alias_value":"NYGUT64WM7K7M5OD","created_at":"2026-07-05T04:31:20.183309+00:00"},{"alias_kind":"pith_short_8","alias_value":"NYGUT64W","created_at":"2026-07-05T04:31:20.183309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.14148","citing_title":"Acoustic scattering AI for non-invasive object classifications: A case study on hair assessment","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12159","citing_title":"VidTAG: Temporally Aligned Video to GPS Geolocalization with Denoising Sequence Prediction at a Global Scale","ref_index":58,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NYGUT64WM7K7M5ODH7ILZEIPZF","json":"https://pith.science/pith/NYGUT64WM7K7M5ODH7ILZEIPZF.json","graph_json":"https://pith.science/api/pith-number/NYGUT64WM7K7M5ODH7ILZEIPZF/graph.json","events_json":"https://pith.science/api/pith-number/NYGUT64WM7K7M5ODH7ILZEIPZF/events.json","paper":"https://pith.science/paper/NYGUT64W"},"agent_actions":{"view_html":"https://pith.science/pith/NYGUT64WM7K7M5ODH7ILZEIPZF","download_json":"https://pith.science/pith/NYGUT64WM7K7M5ODH7ILZEIPZF.json","view_paper":"https://pith.science/paper/NYGUT64W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.05171&json=true","fetch_graph":"https://pith.science/api/pith-number/NYGUT64WM7K7M5ODH7ILZEIPZF/graph.json","fetch_events":"https://pith.science/api/pith-number/NYGUT64WM7K7M5ODH7ILZEIPZF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NYGUT64WM7K7M5ODH7ILZEIPZF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NYGUT64WM7K7M5ODH7ILZEIPZF/action/storage_attestation","attest_author":"https://pith.science/pith/NYGUT64WM7K7M5ODH7ILZEIPZF/action/author_attestation","sign_citation":"https://pith.science/pith/NYGUT64WM7K7M5ODH7ILZEIPZF/action/citation_signature","submit_replication":"https://pith.science/pith/NYGUT64WM7K7M5ODH7ILZEIPZF/action/replication_record"}},"created_at":"2026-07-05T04:31:20.183309+00:00","updated_at":"2026-07-05T04:31:20.183309+00:00"}