Saved in:
Bibliographic Details
Main Authors: Wu, Ke, Variani, Ehsan, Bagby, Tom, Reddy, Shashir, Pilgrim, Rory
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.16555
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914571302731776
author Wu, Ke
Variani, Ehsan
Bagby, Tom
Reddy, Shashir
Pilgrim, Rory
author_facet Wu, Ke
Variani, Ehsan
Bagby, Tom
Reddy, Shashir
Pilgrim, Rory
contents We present MedASR, an open-source 105M-parameter model engineered for high-accuracy medical dictation. Prioritizing a "small, fast, and accurate" design, MedASR addresses 3 core pillars (1) Data: overcoming clinical corpora scarcity and class imbalance; (2) Modeling: efficient long-form training; and (3) Inference: accurate transcription via a pseudo-streaming sliding-window approach. Our evaluation shows that MedASR achieves a 58% relative WER reduction on Eye Gaze compared to Whisper Large-v3. By open-sourcing MedASR, we provide a transparent, high-performance backbone for specialized health-care applications, breaking down the barriers to clinical documentation often obscured by proprietary systems.
format Preprint
id arxiv_https___arxiv_org_abs_2605_16555
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MedASR: An Open-Source Model for High-Accuracy Medical Dictation
Wu, Ke
Variani, Ehsan
Bagby, Tom
Reddy, Shashir
Pilgrim, Rory
Audio and Speech Processing
We present MedASR, an open-source 105M-parameter model engineered for high-accuracy medical dictation. Prioritizing a "small, fast, and accurate" design, MedASR addresses 3 core pillars (1) Data: overcoming clinical corpora scarcity and class imbalance; (2) Modeling: efficient long-form training; and (3) Inference: accurate transcription via a pseudo-streaming sliding-window approach. Our evaluation shows that MedASR achieves a 58% relative WER reduction on Eye Gaze compared to Whisper Large-v3. By open-sourcing MedASR, we provide a transparent, high-performance backbone for specialized health-care applications, breaking down the barriers to clinical documentation often obscured by proprietary systems.
title MedASR: An Open-Source Model for High-Accuracy Medical Dictation
topic Audio and Speech Processing
url https://arxiv.org/abs/2605.16555