Text-to-Speech on SEED-TTS
1.2WERQwen3-TTS-1.7B
Evaluation results
| Method | Links | |
|---|---|---|
| Qwen3-TTS-1.7BCategory=TTS-Experts2026.03 | 1.2 | |
| MiniMax-SpeechCategory=TTS-Experts2026.03 | 1.7 | |
| Qwen2.5-Omni-7BCategory=Perception-centric2026.03 | 2.3 | |
| MaskGCTCategory=TTS-Experts2026.03 | 2.6 | |
| Llasa-8BCategory=TTS-Experts2026.03 | 3 | |
| Dynin-OmniCategory=Unified, Block size=128, Diffusion steps=5122026.03 | 4.3 | |
| HyperCLOVAX-8B-OmniCategory=Unified, Reproduction=‡2026.03 | 7.7 |