{"id":"https://openalex.org/W7170190191","doi":"https://doi.org/10.1515/comp-2025-0060","title":"Fine-tuning Whisper model for end-to-end Kannada to English speech transcription","display_name":"Fine-tuning Whisper model for end-to-end Kannada to English speech transcription","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7170190191","doi":"https://doi.org/10.1515/comp-2025-0060"},"language":"en","primary_location":{"id":"doi:10.1515/comp-2025-0060","is_oa":true,"landing_page_url":"https://doi.org/10.1515/comp-2025-0060","pdf_url":null,"source":{"id":"https://openalex.org/S4210177004","display_name":"Open Computer Science","issn_l":"2299-1093","issn":["2299-1093"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310313990","host_organization_name":"De Gruyter","host_organization_lineage":["https://openalex.org/P4310313990"],"host_organization_lineage_names":["De Gruyter"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Open Computer Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1515/comp-2025-0060","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5143507967","display_name":"Raghurama Holla","orcid":null},"institutions":[{"id":"https://openalex.org/I164861460","display_name":"Manipal Academy of Higher Education","ror":"https://ror.org/02xzytt36","country_code":"IN","type":"education","lineage":["https://openalex.org/I164861460"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Raghurama Holla","raw_affiliation_strings":["Manipal Institute of Technology , Manipal Academy of Higher Education , Manipal , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Manipal Institute of Technology , Manipal Academy of Higher Education , Manipal , India","institution_ids":["https://openalex.org/I164861460"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143492738","display_name":"R. Agam","orcid":null},"institutions":[{"id":"https://openalex.org/I1333540553","display_name":"Nitte University","ror":"https://ror.org/029nydt37","country_code":"IN","type":"education","lineage":["https://openalex.org/I1333540553"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"R. Agam","raw_affiliation_strings":["Department of CSE , NMAMIT, Nitte , Karkala , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of CSE , NMAMIT, Nitte , Karkala , India","institution_ids":["https://openalex.org/I1333540553"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143475432","display_name":"Bianca Gelesia Martis","orcid":null},"institutions":[{"id":"https://openalex.org/I1333540553","display_name":"Nitte University","ror":"https://ror.org/029nydt37","country_code":"IN","type":"education","lineage":["https://openalex.org/I1333540553"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Bianca Gelesia Martis","raw_affiliation_strings":["Department of CSE , NMAMIT, Nitte , Karkala , India","Department of ISE , NMAMIT, Nitte , Karkala , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of CSE , NMAMIT, Nitte , Karkala , India","institution_ids":["https://openalex.org/I1333540553"]},{"raw_affiliation_string":"Department of ISE , NMAMIT, Nitte , Karkala , India","institution_ids":["https://openalex.org/I1333540553"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143470527","display_name":"Britney Genelia Martis","orcid":null},"institutions":[{"id":"https://openalex.org/I1333540553","display_name":"Nitte University","ror":"https://ror.org/029nydt37","country_code":"IN","type":"education","lineage":["https://openalex.org/I1333540553"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Britney Genelia Martis","raw_affiliation_strings":["Department of CSE , NMAMIT, Nitte , Karkala , India","Department of ISE , NMAMIT, Nitte , Karkala , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of CSE , NMAMIT, Nitte , Karkala , India","institution_ids":["https://openalex.org/I1333540553"]},{"raw_affiliation_string":"Department of ISE , NMAMIT, Nitte , Karkala , India","institution_ids":["https://openalex.org/I1333540553"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108627268","display_name":"S. Muralikrishna","orcid":null},"institutions":[{"id":"https://openalex.org/I164861460","display_name":"Manipal Academy of Higher Education","ror":"https://ror.org/02xzytt36","country_code":"IN","type":"education","lineage":["https://openalex.org/I164861460"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S.N. Muralikrishna","raw_affiliation_strings":["Manipal Institute of Technology , Manipal Academy of Higher Education , Manipal , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Manipal Institute of Technology , Manipal Academy of Higher Education , Manipal , India","institution_ids":["https://openalex.org/I164861460"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040926970","display_name":"Raghavendra Ganiga","orcid":"https://orcid.org/0000-0003-4748-6733"},"institutions":[{"id":"https://openalex.org/I164861460","display_name":"Manipal Academy of Higher Education","ror":"https://ror.org/02xzytt36","country_code":"IN","type":"education","lineage":["https://openalex.org/I164861460"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Raghavendra Ganiga","raw_affiliation_strings":["Manipal Institute of Technology , Manipal Academy of Higher Education , Manipal , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Manipal Institute of Technology , Manipal Academy of Higher Education , Manipal , India","institution_ids":["https://openalex.org/I164861460"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1050,"currency":"EUR","value_usd":1187},"apc_paid":{"value":1050,"currency":"EUR","value_usd":1187},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.79542894,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"16","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8892999887466431,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8892999887466431,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.027899999171495438,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.006200000178068876,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/kannada","display_name":"Kannada","score":0.7706000208854675},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.7213000059127808},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.7208999991416931},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4952000081539154},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.41269999742507935},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.36329999566078186},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.3456000089645386},{"id":"https://openalex.org/keywords/error-analysis","display_name":"Error analysis","score":0.32420000433921814}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.782800018787384},{"id":"https://openalex.org/C2778579358","wikidata":"https://www.wikidata.org/wiki/Q33673","display_name":"Kannada","level":2,"score":0.7706000208854675},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.7213000059127808},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.7208999991416931},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6453999876976013},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6061999797821045},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5410000085830688},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4952000081539154},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.41269999742507935},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.36329999566078186},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.3456000089645386},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.32420000433921814},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C2777853878","wikidata":"https://www.wikidata.org/wiki/Q743569","display_name":"Phonetic transcription","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.25949999690055847},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.25920000672340393},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2554999887943268}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1515/comp-2025-0060","is_oa":true,"landing_page_url":"https://doi.org/10.1515/comp-2025-0060","pdf_url":null,"source":{"id":"https://openalex.org/S4210177004","display_name":"Open Computer Science","issn_l":"2299-1093","issn":["2299-1093"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310313990","host_organization_name":"De Gruyter","host_organization_lineage":["https://openalex.org/P4310313990"],"host_organization_lineage_names":["De Gruyter"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Open Computer Science","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:2ae6106ba39d4d3ab749d906818b3f05","is_oa":false,"landing_page_url":"https://doaj.org/article/2ae6106ba39d4d3ab749d906818b3f05","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Open Computer Science, Vol 16, Iss 1, Pp 28492-28518 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1515/comp-2025-0060","is_oa":true,"landing_page_url":"https://doi.org/10.1515/comp-2025-0060","pdf_url":null,"source":{"id":"https://openalex.org/S4210177004","display_name":"Open Computer Science","issn_l":"2299-1093","issn":["2299-1093"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310313990","host_organization_name":"De Gruyter","host_organization_lineage":["https://openalex.org/P4310313990"],"host_organization_lineage_names":["De Gruyter"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Open Computer Science","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7724449038505554,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2962784628","https://openalex.org/W2963250244","https://openalex.org/W3048539749","https://openalex.org/W3147984406","https://openalex.org/W3198429080","https://openalex.org/W3213029956","https://openalex.org/W4360951492","https://openalex.org/W4390548232","https://openalex.org/W4391698383","https://openalex.org/W4392669897","https://openalex.org/W4392904451","https://openalex.org/W4393302626","https://openalex.org/W4399265137","https://openalex.org/W4399291929","https://openalex.org/W4402981815","https://openalex.org/W4405179268","https://openalex.org/W4408345664","https://openalex.org/W4415433959","https://openalex.org/W7126440343"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Building":[1],"reliable":[2],"automatic":[3],"speech":[4,44,150],"recognition":[5],"(ASR)":[6],"systems":[7],"for":[8,130,145],"low-resource":[9,134],"languages":[10,136],"such":[11],"as":[12],"Kannada":[13,50],"is":[14],"challenging":[15],"due":[16],"to":[17,40,58,103,115],"the":[18,24,52,67,86,92,95,98,105,116,122],"scarcity":[19],"of":[20,49,66,94,124],"training":[21],"data":[22],"and":[23,37,61,77,112,126,137],"cross-lingual":[25,131],"translation":[26,62],"requirements.":[27],"This":[28],"study":[29],"investigates":[30],"fine-tuning":[31],"Whisper":[32,54,128],"models":[33,55,69,141],"\u2013":[34,39],"Tiny,":[35],"Small,":[36],"Medium":[38],"achieve":[41],"end-to-end":[42],"Kannada-to-English":[43],"transcription.":[45],"Using":[46],"a":[47],"dataset":[48],"speech,":[51],"multilingual":[53,149],"are":[56,142],"fine-tuned":[57,68],"improve":[59],"transcription":[60],"performance.":[63],"The":[64,119],"accuracy":[65],"was":[70,101],"evaluated":[71],"using":[72],"word":[73],"error":[74,79],"rate":[75,80],"(WER)":[76],"character":[78],"(CER),":[81],"revealing":[82],"clear":[83],"improvements":[84],"across":[85],"different":[87],"model":[88,100],"sizes.":[89],"Based":[90],"on":[91],"analysis":[93],"experimental":[96],"results,":[97],"Whisper-Medium":[99],"found":[102],"perform":[104],"best,":[106],"with":[107],"significant":[108],"reductions":[109],"in":[110,133,148],"WER":[111],"CER":[113],"compared":[114],"zero-shot":[117],"baselines.":[118],"results":[120],"highlight":[121],"feasibility":[123],"lightweight":[125],"midsize":[127],"architectures":[129],"ASR":[132],"Indian":[135],"indicate":[138],"that":[139],"these":[140],"more":[143],"suitable":[144],"real-world":[146],"applications":[147],"systems.":[151]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-07-24T00:00:00"}
