MedScribe AI
A clinician-led AI company pioneering ambient clinical documentation, processing hundreds of thousands of clinical encounters weekly across dozens of health systems.
Multilingual Performance
Updated 5 min ago via Autoblocks
Overview
Test Description
Measures accuracy across different languages.
Key Metrics
Average Cross-lingual Performance
1% better than state-of-the-art
Evaluation
Methodology
Comparative analysis against gold standard transcripts across multiple languages, using both benchmark datasets and real-world clinical conversations.
Interpretation of scores
Performance matches or exceeds industry standards across supported languages, with particularly strong performance in Spanish.
Dataset
Dataset Description
Evaluated using FLEURS dataset (102 languages) and real-world clinical conversations in multiple languages.
Dimensions
Language
English13.7% WER
Spanish3.6% WER
Vietnamese≤ Industry Standard
Tagalog≤ Industry Standard