Audio+caption guided speech generation on A-I-TTS
89SIMUniAudio 2.0 (Ours 3B)
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| UniAudio 2.0 (Ours 3B)mode=Zero-shot, parameters=3B2026.02 | 89 | 32.62 | 11.57 | 2.87 | |
| UniAudio 2.0mode=Zero-shot2026.02 | 89 | 32.62 | 11.57 | 2.87 | |
| Ablation (Ours 1B)mode=Zero-shot, parameters=1B2026.02 | 62 | 5.2 | 14.8 | 2.43 |