Speech Recognition On Swb_Hub_500 Wer
Metrics
Percentage error
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Percentage error |
|---|---|
| building-dnn-acoustic-models-for-large | 19.1 |
| deep-speech-scaling-up-end-to-end-speech | 16 |
| Model 3 | 17.1 |
| Model 4 | 18.4 |
| on-the-limit-of-english-conversational-speech | 6.8 |
| the-ibm-2016-english-conversational-telephone | 12.2 |
| english-conversational-telephone-speech | 10.3 |
| the-microsoft-2016-conversational-speech | 11.9 |
| Model 9 | 13 |
| Model 10 | 13.3 |
| Model 11 | 19.3 |
| single-headed-attention-based-sequence-to | 7.8 |