{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/fine-tuning-whisper-on-low-resource-languages","title":"Fine-tuning Whisper on Low-Resource Languages for Real-World Applications","arxiv_id":"2412.15726","date":"2024-12-20","proceeding":null,"authors":["Vincenzo Timmel","Claudio Paonessa","Reza kakooee","Manfred Vogel","Daniel Perruchoud"],"abstract":"This paper presents a new approach to fine-tuning OpenAI's Whisper model for low-resource languages by introducing a novel data generation method that converts sentence-level data into a long-form corpus, using Swiss German as a case study. Non-sentence-level data, which could improve the performance of long-form audio, is difficult to obtain and often restricted by copyright laws. Our method bridges this gap by transforming more accessible sentence-level data into a format that preserves the model's ability to handle long-form audio and perform segmentation without requiring non-sentence-level data. Our data generation process improves performance in several real-world applications and leads to the development of a new state-of-the-art speech-to-text (STT) model for Swiss German. We compare our model with a non-fine-tuned Whisper and our previous state-of-the-art Swiss German STT models, where our new model achieves higher BLEU scores. Our results also indicate that the proposed method is adaptable to other low-resource languages, supported by written guidance and code that allows the creation of fine-tuned Whisper models, which keep segmentation capabilities and allow the transcription of longer audio files using only sentence-level data with high quality.","url_abs":"https://arxiv.org/abs/2412.15726v3","url_pdf":"https://arxiv.org/pdf/2412.15726v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"fine-tuning-whisper-on-low-resource-languages","repo_url":"https://github.com/i4ds/whisper-finetune","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"form","task_name":"Form"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"speech-to-text","task_name":"Speech-to-Text"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2412.15726","atlas_url":"https://app.syntology.ai/?focus=2412.15726","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}