{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FI5VOSIFGMVESK3NCRDFVFQPKH","short_pith_number":"pith:FI5VOSIF","schema_version":"1.0","canonical_sha256":"2a3b574905332a492b6d14465a960f51f70d7aef147c9087a390cf62add46bd9","source":{"kind":"arxiv","id":"2401.16658","version":3},"attestation_state":"computed","paper":{"title":"OWSM v3.1: Better and Faster Open Whisper-Style Speech Models based on E-Branchformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Brian Yan, Jee-weon Jung, Jiatong Shi, Jinchuan Tian, Kwanghee Choi, Muhammad Shakeel, Shinji Watanabe, Siddhant Arora, William Chen, Xuankai Chang, Yifan Peng, Yui Sudo","submitted_at":"2024-01-30T01:22:18Z","abstract_excerpt":"Recent studies have highlighted the importance of fully open foundation models. The Open Whisper-style Speech Model (OWSM) is an initial step towards reproducing OpenAI Whisper using public data and open-source toolkits. However, previous versions of OWSM (v1 to v3) are still based on standard Transformer, which might lead to inferior performance compared to state-of-the-art speech encoder architectures. This work aims to improve the performance and efficiency of OWSM without additional data. We present a series of E-Branchformer-based models named OWSM v3.1, ranging from 100M to 1B parameters"},"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":"2401.16658","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-30T01:22:18Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"70842beddef145ee42c9931841f31cc4b038bb0a7aac3b233f3f51bc04db5270","abstract_canon_sha256":"36c8c6cdd648a589bc915edb799f04535cffc40e2af17d2b65d1f51afed859e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:59:25.778766Z","signature_b64":"LJ5MtOX5BUNDohg66qnnKjnsxE8woNLz2uNgtRqOU74OZlbww044tfHg9EkAg4FMulsQWC2WG+VemY8YflmxDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a3b574905332a492b6d14465a960f51f70d7aef147c9087a390cf62add46bd9","last_reissued_at":"2026-07-05T08:59:25.778167Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:59:25.778167Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OWSM v3.1: Better and Faster Open Whisper-Style Speech Models based on E-Branchformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Brian Yan, Jee-weon Jung, Jiatong Shi, Jinchuan Tian, Kwanghee Choi, Muhammad Shakeel, Shinji Watanabe, Siddhant Arora, William Chen, Xuankai Chang, Yifan Peng, Yui Sudo","submitted_at":"2024-01-30T01:22:18Z","abstract_excerpt":"Recent studies have highlighted the importance of fully open foundation models. The Open Whisper-style Speech Model (OWSM) is an initial step towards reproducing OpenAI Whisper using public data and open-source toolkits. However, previous versions of OWSM (v1 to v3) are still based on standard Transformer, which might lead to inferior performance compared to state-of-the-art speech encoder architectures. This work aims to improve the performance and efficiency of OWSM without additional data. We present a series of E-Branchformer-based models named OWSM v3.1, ranging from 100M to 1B parameters"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.16658","kind":"arxiv","version":3},"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/2401.16658/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":"2401.16658","created_at":"2026-07-05T08:59:25.778248+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.16658v3","created_at":"2026-07-05T08:59:25.778248+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.16658","created_at":"2026-07-05T08:59:25.778248+00:00"},{"alias_kind":"pith_short_12","alias_value":"FI5VOSIFGMVE","created_at":"2026-07-05T08:59:25.778248+00:00"},{"alias_kind":"pith_short_16","alias_value":"FI5VOSIFGMVESK3N","created_at":"2026-07-05T08:59:25.778248+00:00"},{"alias_kind":"pith_short_8","alias_value":"FI5VOSIF","created_at":"2026-07-05T08:59:25.778248+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20830","citing_title":"Raon-OpenTTS: Open Models and Data for Robust Text-to-Speech","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FI5VOSIFGMVESK3NCRDFVFQPKH","json":"https://pith.science/pith/FI5VOSIFGMVESK3NCRDFVFQPKH.json","graph_json":"https://pith.science/api/pith-number/FI5VOSIFGMVESK3NCRDFVFQPKH/graph.json","events_json":"https://pith.science/api/pith-number/FI5VOSIFGMVESK3NCRDFVFQPKH/events.json","paper":"https://pith.science/paper/FI5VOSIF"},"agent_actions":{"view_html":"https://pith.science/pith/FI5VOSIFGMVESK3NCRDFVFQPKH","download_json":"https://pith.science/pith/FI5VOSIFGMVESK3NCRDFVFQPKH.json","view_paper":"https://pith.science/paper/FI5VOSIF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.16658&json=true","fetch_graph":"https://pith.science/api/pith-number/FI5VOSIFGMVESK3NCRDFVFQPKH/graph.json","fetch_events":"https://pith.science/api/pith-number/FI5VOSIFGMVESK3NCRDFVFQPKH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FI5VOSIFGMVESK3NCRDFVFQPKH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FI5VOSIFGMVESK3NCRDFVFQPKH/action/storage_attestation","attest_author":"https://pith.science/pith/FI5VOSIFGMVESK3NCRDFVFQPKH/action/author_attestation","sign_citation":"https://pith.science/pith/FI5VOSIFGMVESK3NCRDFVFQPKH/action/citation_signature","submit_replication":"https://pith.science/pith/FI5VOSIFGMVESK3NCRDFVFQPKH/action/replication_record"}},"created_at":"2026-07-05T08:59:25.778248+00:00","updated_at":"2026-07-05T08:59:25.778248+00:00"}