Text-to-Speech on Common Voice en 15
10.8WERPhi-4 Multimodal
Evaluation Results
| Method | Links | |
|---|---|---|
| Phi-4 Multimodal2026.01 | 10.8 | |
| MoST2026.01 | 11.5 | |
| SeamlessM4T-v22026.01 | 12.1 | |
| MinMo2026.01 | 13.5 | |
| Moshi2026.01 | 14.2 | |
| LLaMA-Omni22026.01 | 17.2 | |
| SpiritLM2026.01 | 22.4 | |
| SpeechGPT2026.01 | 23.2 | |
| AudioLM2026.01 | 25.1 |