Build Your Own AI Trust Center

Demonstrate your commitment to AI safety and transparency with a customized trust center

Banner

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