{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QLXW7DYTYXURAK55MGNVLPMFUG","short_pith_number":"pith:QLXW7DYT","schema_version":"1.0","canonical_sha256":"82ef6f8f13c5e9102bbd619b55bd85a1a80a21339772225f2c0a8c7b93b2ffb5","source":{"kind":"arxiv","id":"2305.15386","version":2},"attestation_state":"computed","paper":{"title":"Vistaar: Diverse Benchmarks and Training Sets for Indian Language ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Abhigyan Raman, Kaushal Santosh Bhogale, Mitesh M. Khapra, Pratyush Kumar, Sai Sundaresan, Tahir Javed","submitted_at":"2023-05-24T17:46:03Z","abstract_excerpt":"Improving ASR systems is necessary to make new LLM-based use-cases accessible to people across the globe. In this paper, we focus on Indian languages, and make the case that diverse benchmarks are required to evaluate and improve ASR systems for Indian languages. To address this, we collate Vistaar as a set of 59 benchmarks across various language and domain combinations, on which we evaluate 3 publicly available ASR systems and 2 commercial systems. We also train IndicWhisper models by fine-tuning the Whisper models on publicly available training datasets across 12 Indian languages totalling "},"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":"2305.15386","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T17:46:03Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"31891d7b96d31392bb89651cb997f29ff19701cb4960a72c54de3d871143ee4e","abstract_canon_sha256":"8284dabc2ff770d3f51c10e0ddf16710878bf9f57c314285cd2e24d5a6456938"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:37:04.164275Z","signature_b64":"oBkIrtKkDuxIZVnxRF2DcX3Z5/+3PK21VsAplwfLMMCH1Q3RK0VSOxyhjdGMBrNNEnG6+VQ9GKCtJAg+X5kYCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82ef6f8f13c5e9102bbd619b55bd85a1a80a21339772225f2c0a8c7b93b2ffb5","last_reissued_at":"2026-07-05T06:37:04.163767Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:37:04.163767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vistaar: Diverse Benchmarks and Training Sets for Indian Language ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Abhigyan Raman, Kaushal Santosh Bhogale, Mitesh M. Khapra, Pratyush Kumar, Sai Sundaresan, Tahir Javed","submitted_at":"2023-05-24T17:46:03Z","abstract_excerpt":"Improving ASR systems is necessary to make new LLM-based use-cases accessible to people across the globe. In this paper, we focus on Indian languages, and make the case that diverse benchmarks are required to evaluate and improve ASR systems for Indian languages. To address this, we collate Vistaar as a set of 59 benchmarks across various language and domain combinations, on which we evaluate 3 publicly available ASR systems and 2 commercial systems. We also train IndicWhisper models by fine-tuning the Whisper models on publicly available training datasets across 12 Indian languages totalling "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15386","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/2305.15386/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":"2305.15386","created_at":"2026-07-05T06:37:04.163829+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.15386v2","created_at":"2026-07-05T06:37:04.163829+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15386","created_at":"2026-07-05T06:37:04.163829+00:00"},{"alias_kind":"pith_short_12","alias_value":"QLXW7DYTYXUR","created_at":"2026-07-05T06:37:04.163829+00:00"},{"alias_kind":"pith_short_16","alias_value":"QLXW7DYTYXURAK55","created_at":"2026-07-05T06:37:04.163829+00:00"},{"alias_kind":"pith_short_8","alias_value":"QLXW7DYT","created_at":"2026-07-05T06:37:04.163829+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21408","citing_title":"Vaani Benchmark V1.0: An Inclusive Multimodal Benchmark Dataset for Hindi","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18659","citing_title":"Responsible ASR: Overcoming Challenges of Foundational Models in Narrow-Band and Low-Resource Settings","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QLXW7DYTYXURAK55MGNVLPMFUG","json":"https://pith.science/pith/QLXW7DYTYXURAK55MGNVLPMFUG.json","graph_json":"https://pith.science/api/pith-number/QLXW7DYTYXURAK55MGNVLPMFUG/graph.json","events_json":"https://pith.science/api/pith-number/QLXW7DYTYXURAK55MGNVLPMFUG/events.json","paper":"https://pith.science/paper/QLXW7DYT"},"agent_actions":{"view_html":"https://pith.science/pith/QLXW7DYTYXURAK55MGNVLPMFUG","download_json":"https://pith.science/pith/QLXW7DYTYXURAK55MGNVLPMFUG.json","view_paper":"https://pith.science/paper/QLXW7DYT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.15386&json=true","fetch_graph":"https://pith.science/api/pith-number/QLXW7DYTYXURAK55MGNVLPMFUG/graph.json","fetch_events":"https://pith.science/api/pith-number/QLXW7DYTYXURAK55MGNVLPMFUG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QLXW7DYTYXURAK55MGNVLPMFUG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QLXW7DYTYXURAK55MGNVLPMFUG/action/storage_attestation","attest_author":"https://pith.science/pith/QLXW7DYTYXURAK55MGNVLPMFUG/action/author_attestation","sign_citation":"https://pith.science/pith/QLXW7DYTYXURAK55MGNVLPMFUG/action/citation_signature","submit_replication":"https://pith.science/pith/QLXW7DYTYXURAK55MGNVLPMFUG/action/replication_record"}},"created_at":"2026-07-05T06:37:04.163829+00:00","updated_at":"2026-07-05T06:37:04.163829+00:00"}