Text-to-Speech on Emergent-TTS Emotion (test)
0.63WER (%)Semantic-VAE
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Semantic-VAEZero-shot=true2026.05 | 0.63 | 14.3 | |
| HoliTokZero-shot=true2026.05 | 1.34 | 25.5 | |
| MingTok-AudioZero-shot=true2026.05 | 8.81 | 8.4 |
| Method | Links | ||
|---|---|---|---|
| Semantic-VAEZero-shot=true2026.05 | 0.63 | 14.3 | |
| HoliTokZero-shot=true2026.05 | 1.34 | 25.5 | |
| MingTok-AudioZero-shot=true2026.05 | 8.81 | 8.4 |