{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YYSBKCLEOD6FXSLM26HHEZXVK3","short_pith_number":"pith:YYSBKCLE","schema_version":"1.0","canonical_sha256":"c62415096470fc5bc96cd78e7266f556d6ae56b3b6b3a3493039c033332842f1","source":{"kind":"arxiv","id":"2409.09506","version":1},"attestation_state":"computed","paper":{"title":"ESPnet-EZ: Python-only ESPnet for Easy Fine-tuning and Integration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jiatong Shi, Jionghao Han, Kwanghee Choi, Masao Someki, Samuele Cornell, Shinji Watanabe, Siddhant Arora, Vaibhav Srivastav, William Chen, Yifan Peng","submitted_at":"2024-09-14T19:03:53Z","abstract_excerpt":"We introduce ESPnet-EZ, an extension of the open-source speech processing toolkit ESPnet, aimed at quick and easy development of speech models. ESPnet-EZ focuses on two major aspects: (i) easy fine-tuning and inference of existing ESPnet models on various tasks and (ii) easy integration with popular deep neural network frameworks such as PyTorch-Lightning, Hugging Face transformers and datasets, and Lhotse. By replacing ESPnet design choices inherited from Kaldi with a Python-only, Bash-free interface, we dramatically reduce the effort required to build, debug, and use a new model. For example"},"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":"2409.09506","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-14T19:03:53Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"afa620d3a191c3b78916fd3867180f05a2a7956bf9932c1c3d0b6993e318b20e","abstract_canon_sha256":"d3b88c0cbc03cea5be07d82dc75031633932919990c0249f9cdf8b714a66d458"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:07:10.624477Z","signature_b64":"ReZp9Di9hsgGuySRNTjU9D/PG86cG7VXSM8rOT8uNloRoXxyXjn8jX46Ez162iyfWDH8piVNh3w5BMrjy5+cAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c62415096470fc5bc96cd78e7266f556d6ae56b3b6b3a3493039c033332842f1","last_reissued_at":"2026-07-05T09:07:10.623941Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:07:10.623941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ESPnet-EZ: Python-only ESPnet for Easy Fine-tuning and Integration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jiatong Shi, Jionghao Han, Kwanghee Choi, Masao Someki, Samuele Cornell, Shinji Watanabe, Siddhant Arora, Vaibhav Srivastav, William Chen, Yifan Peng","submitted_at":"2024-09-14T19:03:53Z","abstract_excerpt":"We introduce ESPnet-EZ, an extension of the open-source speech processing toolkit ESPnet, aimed at quick and easy development of speech models. ESPnet-EZ focuses on two major aspects: (i) easy fine-tuning and inference of existing ESPnet models on various tasks and (ii) easy integration with popular deep neural network frameworks such as PyTorch-Lightning, Hugging Face transformers and datasets, and Lhotse. By replacing ESPnet design choices inherited from Kaldi with a Python-only, Bash-free interface, we dramatically reduce the effort required to build, debug, and use a new model. For example"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09506","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/2409.09506/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":"2409.09506","created_at":"2026-07-05T09:07:10.624014+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.09506v1","created_at":"2026-07-05T09:07:10.624014+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09506","created_at":"2026-07-05T09:07:10.624014+00:00"},{"alias_kind":"pith_short_12","alias_value":"YYSBKCLEOD6F","created_at":"2026-07-05T09:07:10.624014+00:00"},{"alias_kind":"pith_short_16","alias_value":"YYSBKCLEOD6FXSLM","created_at":"2026-07-05T09:07:10.624014+00:00"},{"alias_kind":"pith_short_8","alias_value":"YYSBKCLE","created_at":"2026-07-05T09:07:10.624014+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/YYSBKCLEOD6FXSLM26HHEZXVK3","json":"https://pith.science/pith/YYSBKCLEOD6FXSLM26HHEZXVK3.json","graph_json":"https://pith.science/api/pith-number/YYSBKCLEOD6FXSLM26HHEZXVK3/graph.json","events_json":"https://pith.science/api/pith-number/YYSBKCLEOD6FXSLM26HHEZXVK3/events.json","paper":"https://pith.science/paper/YYSBKCLE"},"agent_actions":{"view_html":"https://pith.science/pith/YYSBKCLEOD6FXSLM26HHEZXVK3","download_json":"https://pith.science/pith/YYSBKCLEOD6FXSLM26HHEZXVK3.json","view_paper":"https://pith.science/paper/YYSBKCLE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.09506&json=true","fetch_graph":"https://pith.science/api/pith-number/YYSBKCLEOD6FXSLM26HHEZXVK3/graph.json","fetch_events":"https://pith.science/api/pith-number/YYSBKCLEOD6FXSLM26HHEZXVK3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YYSBKCLEOD6FXSLM26HHEZXVK3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YYSBKCLEOD6FXSLM26HHEZXVK3/action/storage_attestation","attest_author":"https://pith.science/pith/YYSBKCLEOD6FXSLM26HHEZXVK3/action/author_attestation","sign_citation":"https://pith.science/pith/YYSBKCLEOD6FXSLM26HHEZXVK3/action/citation_signature","submit_replication":"https://pith.science/pith/YYSBKCLEOD6FXSLM26HHEZXVK3/action/replication_record"}},"created_at":"2026-07-05T09:07:10.624014+00:00","updated_at":"2026-07-05T09:07:10.624014+00:00"}