{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KDDCQ67TOY4M3XN4P7OTMCHLRH","short_pith_number":"pith:KDDCQ67T","schema_version":"1.0","canonical_sha256":"50c6287bf37638cdddbc7fdd3608eb89f94a49de8dc5984a2676ab282d84a025","source":{"kind":"arxiv","id":"2507.01931","version":1},"attestation_state":"computed","paper":{"title":"Adaptability of ASR Models on Low-Resource Language: A Comparative Study of Whisper and Wav2Vec-BERT on Bangla","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Md. Aminur Rahman, Md Sazzadul Islam Ridoy, Sumi Akter","submitted_at":"2025-07-02T17:44:54Z","abstract_excerpt":"In recent years, neural models trained on large multilingual text and speech datasets have shown great potential for supporting low-resource languages. This study investigates the performances of two state-of-the-art Automatic Speech Recognition (ASR) models, OpenAI's Whisper (Small & Large-V2) and Facebook's Wav2Vec-BERT on Bangla, a low-resource language. We have conducted experiments using two publicly available datasets: Mozilla Common Voice-17 and OpenSLR to evaluate model performances. Through systematic fine-tuning and hyperparameter optimization, including learning rate, epochs, and mo"},"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":"2507.01931","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-02T17:44:54Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"1566efa4bd115a58069c7ef619bab22c30569359fcd2f64a21d3ddedbaad1422","abstract_canon_sha256":"33654245b6c64208fb815791d2bc3444ad9387e1423900a1ec0c493b556086ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:58.387005Z","signature_b64":"FNgPHGnSCI1n22a6DmDiND+B/LbZqPcx6D5kcAvXP96SMvdj7X1rxoX/wKPwJQfPkE1pYqFKUiIwWUw/hxwFAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50c6287bf37638cdddbc7fdd3608eb89f94a49de8dc5984a2676ab282d84a025","last_reissued_at":"2026-07-05T11:30:58.386516Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:58.386516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptability of ASR Models on Low-Resource Language: A Comparative Study of Whisper and Wav2Vec-BERT on Bangla","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Md. Aminur Rahman, Md Sazzadul Islam Ridoy, Sumi Akter","submitted_at":"2025-07-02T17:44:54Z","abstract_excerpt":"In recent years, neural models trained on large multilingual text and speech datasets have shown great potential for supporting low-resource languages. This study investigates the performances of two state-of-the-art Automatic Speech Recognition (ASR) models, OpenAI's Whisper (Small & Large-V2) and Facebook's Wav2Vec-BERT on Bangla, a low-resource language. We have conducted experiments using two publicly available datasets: Mozilla Common Voice-17 and OpenSLR to evaluate model performances. Through systematic fine-tuning and hyperparameter optimization, including learning rate, epochs, and mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01931","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/2507.01931/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":"2507.01931","created_at":"2026-07-05T11:30:58.386577+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.01931v1","created_at":"2026-07-05T11:30:58.386577+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01931","created_at":"2026-07-05T11:30:58.386577+00:00"},{"alias_kind":"pith_short_12","alias_value":"KDDCQ67TOY4M","created_at":"2026-07-05T11:30:58.386577+00:00"},{"alias_kind":"pith_short_16","alias_value":"KDDCQ67TOY4M3XN4","created_at":"2026-07-05T11:30:58.386577+00:00"},{"alias_kind":"pith_short_8","alias_value":"KDDCQ67T","created_at":"2026-07-05T11:30:58.386577+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24244","citing_title":"When Surveys Become Conversations: Adaptive Matrix Validation for AI-Assisted Interviews","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KDDCQ67TOY4M3XN4P7OTMCHLRH","json":"https://pith.science/pith/KDDCQ67TOY4M3XN4P7OTMCHLRH.json","graph_json":"https://pith.science/api/pith-number/KDDCQ67TOY4M3XN4P7OTMCHLRH/graph.json","events_json":"https://pith.science/api/pith-number/KDDCQ67TOY4M3XN4P7OTMCHLRH/events.json","paper":"https://pith.science/paper/KDDCQ67T"},"agent_actions":{"view_html":"https://pith.science/pith/KDDCQ67TOY4M3XN4P7OTMCHLRH","download_json":"https://pith.science/pith/KDDCQ67TOY4M3XN4P7OTMCHLRH.json","view_paper":"https://pith.science/paper/KDDCQ67T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.01931&json=true","fetch_graph":"https://pith.science/api/pith-number/KDDCQ67TOY4M3XN4P7OTMCHLRH/graph.json","fetch_events":"https://pith.science/api/pith-number/KDDCQ67TOY4M3XN4P7OTMCHLRH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KDDCQ67TOY4M3XN4P7OTMCHLRH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KDDCQ67TOY4M3XN4P7OTMCHLRH/action/storage_attestation","attest_author":"https://pith.science/pith/KDDCQ67TOY4M3XN4P7OTMCHLRH/action/author_attestation","sign_citation":"https://pith.science/pith/KDDCQ67TOY4M3XN4P7OTMCHLRH/action/citation_signature","submit_replication":"https://pith.science/pith/KDDCQ67TOY4M3XN4P7OTMCHLRH/action/replication_record"}},"created_at":"2026-07-05T11:30:58.386577+00:00","updated_at":"2026-07-05T11:30:58.386577+00:00"}