[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-253174-105":3,"detail-sidebar-cat-1-en-105":80,"doc-detail-253174-en":126},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":73,"head_meta":75,"extra_data":77,"updated_unix":79},105,"en","project-closure-report-audio-to-text-whisper-february-2026","Project Closure Report - Audio to text (Whisper) - February 2026","","Formal project closure for the OCUL AIML audio-to-text initiative using Whisper, conducted as a consortially hosted solution through Scholars Portal. The report documents project goals, outcomes, and lessons learned, including pipeline setup, evaluation methodology, and technical documentation for OCUL member libraries. It summarizes performance metrics against success criteria and analyzes questions on time savings, transcription accuracy across English/French and language switching, and sensitivity to fine-tuning. It concludes with guidance for decision-making on deploying Whisper as an ongoing workflow service.",{"@graph":14,"@context":72},[15,34,55],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/template/","Template",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/template/general/","General",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/template/project-closure-report-audio-to-text-whisper-february-2026/253174/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/project-closure-report-audio-to-text-whisper-february-2026/253174.png","ImageObject",442,249,{"name":42,"@type":43},"wps_ap_test_251126_0180","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-09-22","2026-09-13",true,{"@type":52,"interactionType":53,"userInteractionCount":33},"InteractionCounter",{"@type":54},"ViewAction",{"@type":56,"mainEntity":57},"FAQPage",[58,64,68],{"name":59,"@type":60,"acceptedAnswer":61},"What was the purpose of the OCUL AIML audio to text project using Whisper?","Question",{"text":62,"@type":63},"The project aimed to establish a baseline examination of the Whisper audio-to-text tool to enhance digital accessibility in academic libraries. It also supported Scholars Portal’s evaluation of long-term viability for centrally/consortially hosted AI tools and workflows.","Answer",{"name":65,"@type":60,"acceptedAnswer":66},"What were the key deliverables produced during the project?",{"text":67,"@type":63},"Deliverables included setting up a consortially hosted Whisper processing pipeline, creating documentation for Whisper testing and technical use for OCUL member libraries, and leading focused testing of the Whisper ASR system for transcription fit at member libraries.",{"name":69,"@type":60,"acceptedAnswer":70},"What did evaluations conclude about Whisper’s performance and fine-tuning?",{"text":71,"@type":63},"Evaluators reported accuracy exceeded expectations for library materials, with mostly correct wording and minor punctuation issues, while accuracy was weaker for French and when audio switches between languages. The report also notes Whisper is sensitive to fine-tuning, and development efforts led to noticeable performance improvements.","https://schema.org",{"og:url":32,"og:type":74,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":76,"canonical":32},"index,follow",{"doc_id":78,"site_id":7},253174,1789967658,{"code":4,"msg":81,"data":82},"success",[83,88,93,98,103,108,113,118,123],{"id":84,"doc_module":22,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},11,"Presentations",90,"presentations",{"id":89,"doc_module":22,"doc_module_name":25,"category_name":90,"show_sort_weight":91,"slug":92},12,"Resumes",80,"resumes",{"id":94,"doc_module":22,"doc_module_name":25,"category_name":95,"show_sort_weight":96,"slug":97},14,"Invoices",70,"invoices",{"id":99,"doc_module":22,"doc_module_name":25,"category_name":100,"show_sort_weight":101,"slug":102},15,"Posters",60,"posters",{"id":104,"doc_module":22,"doc_module_name":25,"category_name":105,"show_sort_weight":106,"slug":107},16,"Social Media",50,"social-media",{"id":109,"doc_module":22,"doc_module_name":25,"category_name":110,"show_sort_weight":111,"slug":112},17,"Forms",40,"forms",{"id":114,"doc_module":22,"doc_module_name":25,"category_name":115,"show_sort_weight":116,"slug":117},18,"Letters",30,"letters",{"id":119,"doc_module":22,"doc_module_name":25,"category_name":120,"show_sort_weight":121,"slug":122},21,"Paper Templates",5,"papers-templates",{"id":124,"doc_module":22,"doc_module_name":25,"category_name":29,"show_sort_weight":4,"slug":125},158,"general-158",{"code":4,"msg":81,"data":127},{"doc_id":78,"user_id":128,"nickname":42,"user_avatar":129,"doc_module":22,"category_id":124,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":130,"file_id":131,"file_url":132,"file_type":133,"file_size":134,"view_count":26,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":114,"language":135,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":136,"faqs":137,"seo_title":138,"seo_description":12,"update_tm":139,"read_time":140},8796095027276,"https://avatar.qwps.com/avatar/d3BzX2FwX3Rlc3RfMjUxMTI2XzAxODA=","Project Closure Report  \nAudio to text (Whisper)  \nFebruary 2026  \nReport compiled by Kari D. Weaver, Program Manager, Artificial Intelligence and Machine Learning, in collaboration with the Audio to text Project Team.  \nSuggested Citation  \nWeaver, K. D. , Singh, H. , Wang, R. , Xu, M. , McGregor, C. , & Crowley, G. (2026) . Project closure report: Audio to text (Whisper). Ontario Council of University  \nLibraries. [https://docs.scholarsportal.info/Main/OCUL/AIML/Projects/](https://docs.scholarsportal.info/Main/OCUL/AIML/Projects/)  \nAudio_to_Text_Project/  \nTABLE OF CONTENTS  \nProject Closure Report 1 1. Project Overview 3 2. Report Goals 3 3. PROJECT CLOSURE REPORT SUMMARY 3 3.1 Project Background Overview 3 3.2 Project Highlights and Best Practices 3 4. PROJECT METRICS PERFORMANCE 4 4.1 Goals and Objectives Performance 4 4.2 Success Criteria Performance 4 4.3 Milestone and Deliverables Performance 4 4.4 Schedule Performance 4 5. PROJECT CLOSURE TASKS 4 5.1 Resource Management 4 5.2 Issue Management 5 5.3 Lessons Learned 5 5.4 Asset Management 5 5.5 Documentation Archive 5 5.6 Acknowledgements 5  \n1. Project Overview  \nAs a component project of the OCUL Artificial Intelligence and Machine Learning (AIML) Program, the audio to text project is intended to provide a baseline examination of one audio to text AI tool (Whisper) to enhance digital accessibility in the academic library environment while providing information and documentation to OCUL membership and beyond. Additionally, the project will provide Scholars Portal with the opportunity to internally assess the long-term viability of centrally/consortially hosted AI tools and projects like this from a service provider perspective, considering resource and participation requirements, metrics needed for effective evaluation, and project workflows. Considerations may include establishing governance practices, ongoing user support, and decision-making processes related to the selection and management of appropriate tools.  \nTranscriptions of audio files have many use cases for libraries and researchers, including their function as an essential element of digital accessibility. Between April 2025 and December 2025, this project included:  \nꞏ Setting up a pipeline through Scholars Portal to provide a consortially hosted instance of Whisper.  \nꞏ Testing the potential of Whisper to assess its fit for accelerating digital accessibility workflows.  \nꞏ Developing a testing/evaluation and technical documentation for OCUL member libraries.  \nProject Team Leads: Harpinder Singh, Associate Director, Systems and Technical Operations, Scholars Portal (co-lead); Kari Weaver, Project Manager, Artificial Intelligence and Machine Learning, OCUL (co-lead)  \nProject and Development Team Members and Roles: Rachel Wang, Systems Administrator-Devops, Scholars Portal; Meghan Xu, Application Programmer AnalystInfrastructure Services, Scholars Portal; Carlos McGregor, Senior Systems Administrator-Devops, Scholars Portal; Gabby Crowley, Client Services Librarian, Scholars Portal  \nProject Manager: Kari Weaver, Project Manager, Artificial Intelligence and Machine Learning, OCUL (co-lead)  \n2. Report Goals  \nThis report represents a formal conclusion to the AIML audio to text (Whisper) project. In addition, it provides information on the project outcomes, successes, and documents lessons learned from engaging in this exploratory project. Finally, it provides information to support decision making by applicable committees and leaders around establishing the Whisper audio to text workflow as a service.  \n3. Project Closure Report Summary  \n3.1 Project Background Overview  \nThe project had three primary goals. These included:  \n1. Establish a consortially hosted pipeline for Whisper processing.  \n2. Create documentation on Whisper testing and technical use for OCUL member libraries.  \n3. Lead and report on focused testing of the Whisper open-access automatic speech recognition (ASR) system for transcribin","cbCaijPkIXMMr0c4","https://ap.wps.com/l/cbCaijPkIXMMr0c4","pdf",647104,"English","# Project Overview\n# Report Goals\n# Project Closure Report Summary\n## Project Background Overview\n## Project Highlights and Best Practices\n# Project Metrics Performance\n## Goals and Objectives Performance\n## Success Criteria Performance\n## Milestone and Deliverables Performance\n## Schedule Performance\n# Project Closure Tasks\n## Resource Management\n## Issue Management\n## Lessons Learned\n## Asset Management\n## Documentation Archive\n## Acknowledgements","[{\"question\":\"What was the purpose of the OCUL AIML audio to text project using Whisper?\",\"answer\":\"The project aimed to establish a baseline examination of the Whisper audio-to-text tool to enhance digital accessibility in academic libraries. It also supported Scholars Portal’s evaluation of long-term viability for centrally/consortially hosted AI tools and workflows.\"},{\"question\":\"What were the key deliverables produced during the project?\",\"answer\":\"Deliverables included setting up a consortially hosted Whisper processing pipeline, creating documentation for Whisper testing and technical use for OCUL member libraries, and leading focused testing of the Whisper ASR system for transcription fit at member libraries.\"},{\"question\":\"What did evaluations conclude about Whisper’s performance and fine-tuning?\",\"answer\":\"Evaluators reported accuracy exceeded expectations for library materials, with mostly correct wording and minor punctuation issues, while accuracy was weaker for French and when audio switches between languages. The report also notes Whisper is sensitive to fine-tuning, and development efforts led to noticeable performance improvements.\"}]","Project Closure Report - Audio to text (Whisper) - February 2026 | PDF",1789264537,6]