Speech Recognition On Wsj Dev93
Metriken
Word Error Rate (WER)
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | Word Error Rate (WER) |
|---|---|
| crf-based-single-stage-acoustic-modeling-with | 6.23 |
| cat-a-ctc-crf-based-asr-toolkit-bridging-the | 5.7 |
| efficient-neural-architecture-search-for-end | 5.68 |
| fully-convolutional-speech-recognition | 6.8 |