Spoken Language Understanding On Snips 1
المقاييس
Accuracy-EN (%)
Accuracy-FR (%)
النتائج
نتائج أداء النماذج المختلفة على هذا المعيار القياسي
| Paper Title | |||
|---|---|---|---|
| Finstreder (Conformer, character-based) | 87.9 | 86.5 | Finstreder: Simple and fast Spoken Language Understanding with Finite State Transducers using modern Speech-to-Text models |
| Finstreder (Conformer) | 80.4 | 78.3 | Finstreder: Simple and fast Spoken Language Understanding with Finite State Transducers using modern Speech-to-Text models |
| Finstreder (Quartznet) | 77.6 | 77.8 | Finstreder: Simple and fast Spoken Language Understanding with Finite State Transducers using modern Speech-to-Text models |
| Snips | 68.7 | 75.1 | Spoken Language Understanding on the Edge |
| 47.8 | 42.3 | Spoken Language Understanding on the Edge |
0 of 5 row(s) selected.