ML Research Wiki / Benchmarks / Speech Recognition / VietMed

VietMed

Speech Recognition Benchmark

Performance Over Time

📊 Showing 8 results | 📏 Metric: Dev WER

Top Performing Models

Rank Model Paper Dev WER Date Code
1 GMM-HMM Mono VietMed: A Dataset and Benchmark for Automatic Speech Recognition of Vietnamese in the Medical Domain 71.70 2024-04-08 📦 leduckhai/multimed
2 GMM-HMM Tri VietMed: A Dataset and Benchmark for Automatic Speech Recognition of Vietnamese in the Medical Domain 61.30 2024-04-08 📦 leduckhai/multimed
3 GMM-HMM VTLN VietMed: A Dataset and Benchmark for Automatic Speech Recognition of Vietnamese in the Medical Domain 61.30 2024-04-08 📦 leduckhai/multimed
4 GMM-HMM SAT VietMed: A Dataset and Benchmark for Automatic Speech Recognition of Vietnamese in the Medical Domain 52.60 2024-04-08 📦 leduckhai/multimed
5 GMM-HMM SAT+VTLN VietMed: A Dataset and Benchmark for Automatic Speech Recognition of Vietnamese in the Medical Domain 52.20 2024-04-08 📦 leduckhai/multimed
6 w2v2-Viet VietMed: A Dataset and Benchmark for Automatic Speech Recognition of Vietnamese in the Medical Domain 45.30 2024-04-08 📦 leduckhai/multimed
7 XLSR-53 VietMed: A Dataset and Benchmark for Automatic Speech Recognition of Vietnamese in the Medical Domain 45.20 2024-04-08 📦 leduckhai/multimed
8 XLSR-53-Viet VietMed: A Dataset and Benchmark for Automatic Speech Recognition of Vietnamese in the Medical Domain 26.80 2024-04-08 📦 leduckhai/multimed

All Papers (8)

leduckhai/multimed
leduckhai/multimed
leduckhai/multimed
leduckhai/multimed
leduckhai/multimed
leduckhai/multimed
leduckhai/multimed
leduckhai/multimed