EUVIMEDEUVIMED entdecken
Crossref

Fine-Tuning OpenAI Whisper-Small for Domain-Specific Medical Speech Recognition within a Microservice Architecture

Alaeddine Moussa, Noursene Drine

Informatica · 21.02.2026 · 50 (6)

DOI: 10.31449/inf.v50i6.12075 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Informatica, online erschienen am 21.02.2026. Verfasst von Alaeddine Moussa und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We fine-tune Whisper-small (244M parameters) on 8.5 hours of in-domain medical audio and evaluatewith word error rate (WER). Compared to an unadapted Whisper-small baseline, our fine-tuned modelreduces WER from ∼63% to ∼32%. While the relative gain is substantial, this accuracy is not suitablefor unsupervised clinical use; we position the system as a clinician-in-the-loop assistant. We also describedeployment as an on-premise microservice and report latency/throughput considerations.

Zitieren

APA

Moussa, A., & Drine, N. (2026). Fine-Tuning OpenAI Whisper-Small for Domain-Specific Medical Speech Recognition within a Microservice Architecture. Informatica, 50(6). https://doi.org/10.31449/inf.v50i6.12075

Vancouver

Moussa A, Drine N. Fine-Tuning OpenAI Whisper-Small for Domain-Specific Medical Speech Recognition within a Microservice Architecture. Informatica. 2026;50(6). doi:10.31449/inf.v50i6.12075

BibTeX
@article{Moussa2026,
  author = {Moussa, Alaeddine and Drine, Noursene},
  title = {Fine-Tuning OpenAI Whisper-Small for Domain-Specific Medical Speech Recognition within a Microservice Architecture},
  journal = {Informatica},
  year = {2026},
  volume = {50},
  number = {6},
  doi = {10.31449/inf.v50i6.12075}
}
Kostenlos starten →