Automatic Speech Recognition on Average 8 datasets
9.5WERECLM
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| ECLMCorrection model size=0.5B, Decoding strategy=greedy, Base model=Parakeet-TDT-v22024.05 | 9.5 | 13 | |
| Parakeet-TDT-v2Correction method=None2024.05 | 10.9 | — |
Loading the SOTA2 catalog…