Speech Recognition On Chime 6 Eval
Metrics
Word Error Rate (WER)
Results
Performance results of various models on this benchmark
| Paper Title | ||
|---|---|---|
| SpeechStew (1B) | 38.9 | SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network |
| ConformerXXL-PS | 31 | BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition |
| ConformerXXL-PS + G-Augment | 30.7 | G-Augment: Searching for the Meta-Structure of Data Augmentation Policies for ASR |
0 of 3 row(s) selected.