Speech Recognition On Gigaspeech Test
평가 지표
Word Error Rate (WER)
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | Word Error Rate (WER) | Paper Title | Repository |
|---|---|---|---|
| Conformer/Transformer-AED | 10.80 | GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio | |
| Zipformer+CR-CTC (no external language model) | 10.28 | CR-CTC: Consistency regularization on CTC for improved speech recognition | |
| Zipformer+CR-CTC/AED (no external language model) | 10.07 | CR-CTC: Consistency regularization on CTC for improved speech recognition | |
| Zipformer+pruned transducer w/ CR-CTC (no external language model) | 10.03 | CR-CTC: Consistency regularization on CTC for improved speech recognition | |
| Zipformer+pruned transducer (no external language model) | 10.2 | CR-CTC: Consistency regularization on CTC for improved speech recognition |
0 of 5 row(s) selected.