United-MedASR (764M)

Reported on 2 benchmarks across 1 task · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Audio2 results

Speech RecognitiononTedlium
Word Error Rate (WER)· uses extra data· 2024-11-24
0.29
SOTA
High-precision medical speech recognition through synthetic data and semantic correction: UNITED-MEDASR arXiv:2412.00055
Speech RecognitiononEuroparl-ASR EN Guest-test
WER· uses extra data· 2024-11-24
0.26
SOTA
High-precision medical speech recognition through synthetic data and semantic correction: UNITED-MEDASR arXiv:2412.00055