Speech Rate Alignment Prediction on Mandarin Gold (test)
0.733LCCTTS-PRISM
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| TTS-PRISMParameters=7B, Inference Strategy=single-pass inference2026.04 | 0.733 | 0.773 | 0.039 | |
| Gemini-2.5-ProInference Strategy=dimension-wise inference2026.04 | 0.709 | 0.698 | 0.068 | |
| Step-Audio-R1Parameters=33B, Inference Strategy=dimension-wise inference2026.04 | 0.584 | 0.577 | 0.074 | |
| Qwen3-OmniParameters=30B, Inference Strategy=dimension-wise inference2026.04 | 0.403 | 0.385 | 0.054 |