Distant Speech Recognition On Dirha English
Metrics
Word Error Rate (WER)
Results
Performance results of various models on this benchmark
| Paper Title | ||
|---|---|---|
| SincNet-Raw waveform | 38.2 | Interpretable Convolutional Filters with SincNet |
| PASE-FineTuned | 29.8 | Learning Problem-agnostic Speech Representations from Multiple Self-supervised Tasks |
| Li-GRU | 23.9 | The PyTorch-Kaldi Speech Recognition Toolkit |
0 of 3 row(s) selected.