| Paper | Code | Word Error Rate (WER) | ModelName | ReleaseDate |
|---|---|---|---|---|
| High-precision medical speech recognition through synthetic data and semantic correction: UNITED-MEDASR | 0.29 | United-MedASR (764M) | 2024-11-24 | |
| Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition | 3.92 | parakeet-rnnt-1.1b | 2023-05-08 | |
| HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models | ✓ Link | 4.6 | Whispering-LLaMa-7b | 2023-09-27 |
| SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network | 5.3 | SpeechStew (100M) | 2021-04-05 |