Speech Recognition On Tedlium
評価指標
Word Error Rate (WER)
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | Word Error Rate (WER) | Paper Title | Repository |
|---|---|---|---|
| SpeechStew (100M) | 5.3 | SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network | - |
| parakeet-rnnt-1.1b | 3.92 | Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition | - |
| United-MedASR (764M) | 0.29 | High-precision medical speech recognition through synthetic data and semantic correction: UNITED-MEDASR | - |
| Whispering-LLaMa-7b | 4.6 | HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models |
0 of 4 row(s) selected.