Target-Speaker Multilingual Speech Generation on TTS multilingual Portuguese (test)
1.504WERGPT-4o-Audio Preview
Evaluation results
| Method | Links | |
|---|---|---|
| GPT-4o-Audio Preview2026.01 | 1.504 | |
| Qwen3-TTSTokenizer Frequency=25Hz, Parameters=0.6B, Evaluation Protocol=CustomVoice2026.01 | 1.728 | |
| Qwen3-TTSTokenizer Frequency=25Hz, Parameters=1.7B, Evaluation Protocol=CustomVoice2026.01 | 1.854 | |
| Qwen3-TTSTokenizer Frequency=12Hz, Parameters=1.7B, Evaluation Protocol=CustomVoice2026.01 | 2.681 | |
| Qwen3-TTSTokenizer Frequency=12Hz, Parameters=0.6B, Evaluation Protocol=CustomVoice2026.01 | 3.219 |