Automatic Speech Recognition on DefinedAI Banking target domain (test)
9.92WERAdapted model (audio)
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Adapted model (audio)Adaptation=Audio-text pairs2026.01 | 9.92 | 23.6 | |
| Text Denoising AdaptationAdaptation=Text-only2026.01 | 10.11 | 22.1 | |
| Ma et al.Adaptation=Text-only2026.01 | 10.63 | 18.1 | |
| Fang et al.Adaptation=Text-only2026.01 | 10.92 | 15.9 | |
| Base modelAdaptation=None2026.01 | 12.98 | — |