{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7IMPVU4MZIB2RRFOQXFPJF5PNW","short_pith_number":"pith:7IMPVU4M","schema_version":"1.0","canonical_sha256":"fa18fad38cca03a8c4ae85caf497af6db0bb0eb59e4508393af96ed9afe701b1","source":{"kind":"arxiv","id":"2412.19785","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Whisper's Accuracy and Speed for Indian Languages through Prompt-Tuning and Tokenization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Kumud Tripathi, Pankaj Wasnik, Raj Gothi","submitted_at":"2024-12-27T18:32:24Z","abstract_excerpt":"Automatic speech recognition has recently seen a significant advancement with large foundational models such as Whisper. However, these models often struggle to perform well in low-resource languages, such as Indian languages. This paper explores two novel approaches to enhance Whisper's multilingual speech recognition performance in Indian languages. First, we propose prompt-tuning with language family information, which enhances Whisper's accuracy in linguistically similar languages. Second, we introduce a novel tokenizer that reduces the number of generated tokens, thereby accelerating Whis"},"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":"2412.19785","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-27T18:32:24Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"bf853a4679e4074422979042db80fa0bb27c7c22f13fd5f554dee54d451808c1","abstract_canon_sha256":"2b4b1dac3898b0eff57ee16b0e8d99760082e14757122ebdac7a693b10e4431e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:40.996979Z","signature_b64":"0bNZLH4GFmVo+zqk6vhhfWdoexcU+UF9h/0DAxaTuqgc4FEneabu5mJzdzjduAME3u8z/3MnqWxtzD9sewfkBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa18fad38cca03a8c4ae85caf497af6db0bb0eb59e4508393af96ed9afe701b1","last_reissued_at":"2026-07-05T09:54:40.996600Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:40.996600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Whisper's Accuracy and Speed for Indian Languages through Prompt-Tuning and Tokenization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Kumud Tripathi, Pankaj Wasnik, Raj Gothi","submitted_at":"2024-12-27T18:32:24Z","abstract_excerpt":"Automatic speech recognition has recently seen a significant advancement with large foundational models such as Whisper. However, these models often struggle to perform well in low-resource languages, such as Indian languages. This paper explores two novel approaches to enhance Whisper's multilingual speech recognition performance in Indian languages. First, we propose prompt-tuning with language family information, which enhances Whisper's accuracy in linguistically similar languages. Second, we introduce a novel tokenizer that reduces the number of generated tokens, thereby accelerating Whis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19785","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/2412.19785/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":"2412.19785","created_at":"2026-07-05T09:54:40.996656+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.19785v1","created_at":"2026-07-05T09:54:40.996656+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19785","created_at":"2026-07-05T09:54:40.996656+00:00"},{"alias_kind":"pith_short_12","alias_value":"7IMPVU4MZIB2","created_at":"2026-07-05T09:54:40.996656+00:00"},{"alias_kind":"pith_short_16","alias_value":"7IMPVU4MZIB2RRFO","created_at":"2026-07-05T09:54:40.996656+00:00"},{"alias_kind":"pith_short_8","alias_value":"7IMPVU4M","created_at":"2026-07-05T09:54:40.996656+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/7IMPVU4MZIB2RRFOQXFPJF5PNW","json":"https://pith.science/pith/7IMPVU4MZIB2RRFOQXFPJF5PNW.json","graph_json":"https://pith.science/api/pith-number/7IMPVU4MZIB2RRFOQXFPJF5PNW/graph.json","events_json":"https://pith.science/api/pith-number/7IMPVU4MZIB2RRFOQXFPJF5PNW/events.json","paper":"https://pith.science/paper/7IMPVU4M"},"agent_actions":{"view_html":"https://pith.science/pith/7IMPVU4MZIB2RRFOQXFPJF5PNW","download_json":"https://pith.science/pith/7IMPVU4MZIB2RRFOQXFPJF5PNW.json","view_paper":"https://pith.science/paper/7IMPVU4M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.19785&json=true","fetch_graph":"https://pith.science/api/pith-number/7IMPVU4MZIB2RRFOQXFPJF5PNW/graph.json","fetch_events":"https://pith.science/api/pith-number/7IMPVU4MZIB2RRFOQXFPJF5PNW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7IMPVU4MZIB2RRFOQXFPJF5PNW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7IMPVU4MZIB2RRFOQXFPJF5PNW/action/storage_attestation","attest_author":"https://pith.science/pith/7IMPVU4MZIB2RRFOQXFPJF5PNW/action/author_attestation","sign_citation":"https://pith.science/pith/7IMPVU4MZIB2RRFOQXFPJF5PNW/action/citation_signature","submit_replication":"https://pith.science/pith/7IMPVU4MZIB2RRFOQXFPJF5PNW/action/replication_record"}},"created_at":"2026-07-05T09:54:40.996656+00:00","updated_at":"2026-07-05T09:54:40.996656+00:00"}