Speech Recognition On Gigaspeech Dev
평가 지표
Word Error Rate (WER)
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | Word Error Rate (WER) | Paper Title | Repository |
|---|---|---|---|
| Zipformer+pruned transducer w/ CR-CTC (no external language model) | 9.95 | CR-CTC: Consistency regularization on CTC for improved speech recognition | |
| Zipformer+CR-CTC (no external language model) | 10.15 | CR-CTC: Consistency regularization on CTC for improved speech recognition | |
| Zipformer+pruned transducer (no external language model) | 10.09 | CR-CTC: Consistency regularization on CTC for improved speech recognition | |
| SAMBA ASR | 9.12 | Samba-ASR: State-Of-The-Art Speech Recognition Leveraging Structured State-Space Models | - |
| Conformer/Transformer-AED | 10.90 | GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio |
0 of 5 row(s) selected.