Zero-shot Text-to-Speech on MLS De filtered (test)
4.7WERVoicebox (Multilingual)
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Voicebox (Multilingual)Ref (audio context language)=Pl, alpha=12023.06 | 4.7 | 0.491 | |
| Voicebox (Multilingual)Ref (audio context language)=De, alpha=12023.06 | 4.8 | 0.632 | |
| Voicebox (Multilingual)Ref (audio context language)=Es, alpha=12023.06 | 4.9 | 0.46 | |
| Voicebox (Multilingual)Ref (audio context language)=Fr, alpha=12023.06 | 4.9 | 0.476 | |
| Voicebox (Multilingual)Ref (audio context language)=Pt, alpha=12023.06 | 4.9 | 0.422 | |
| Voicebox (Multilingual)Ref (audio context language)=AVG, alpha=12023.06 | 5 | 0.486 | |
| Ground Truth2023.06 | 5.9 | 0.725 | |
| Voicebox (Multilingual)Ref (audio context language)=En, alpha=12023.06 | 5.9 | 0.435 |