Seed-TTS
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Text-to-Speech | Seed-TTS en (test) | WER0.8 | 90 | |
| Text-to-Speech | Seed-TTS zh (test) | WER0.0084 | 65 | |
| Text-to-speech | Seed-TTS (eval) | WER1.85 | 39 | |
| Text-to-Speech | Seed-TTS EN | WER1.7 | 20 | |
| Voice Cloning | SEED-TTS EN (test) | WER0.99 | 16 | |
| Text-to-Speech | Seed-TTS Seed-ZH (Evaluation) | CER0.89 | 16 | |
| Text-to-Speech | Seed-TTS ZH | WER1.07 | 12 | |
| Text-to-Speech | Seed-TTS Seed-ZH (test) | WER1.02 | 11 | |
| Text-to-Speech | Seed-TTS Seed-EN (test) | WER0.0147 | 11 | |
| Text-to-Speech | Seed-TTS 24 kHz (test-zh) | SIM-o0.762 | 11 | |
| Text-to-Speech | Seed-TTS en 24 kHz (test) | SIM-o0.734 | 11 | |
| Text-to-Speech | Seed-TTS-Eval English | WER1.39 | 10 | |
| Voice Conversion | Seed-TTS zh (test) | WER1.33 | 9 | |
| Speech reconstruction | Seed-TTS English | PESQ4.125 | 9 | |
| Speaker Disentanglement | seed-tts-eval | WER2.03 | 8 | |
| Voice Cloning | SEED-TTS-Eval ZH (test) | CER1.03 | 8 | |
| Voice Conversion | Seed-TTS en (test) | WER1.96 | 7 | |
| Text-to-Speech | SEED-TTS | WER1.2 | 7 | |
| Voice Conversion | Seed-TTS English | SECS0.9129 | 7 | |
| Cross-lingual Voice Conversion | Seed-TTS-Eval Chinese-to-English | WER1.14 | 5 | |
| Text-to-Speech | Seed-TTS English (test) | WER2.14 | 5 | |
| TTS Quality Improvement | Seed-TTS MaskGCT | WVMOS4.172 | 5 | |
| TTS Quality Improvement | Seed-TTS MoonCast | WVMOS4.098 | 5 | |
| Cross-lingual Voice Conversion | Seed-TTS English-to-Chinese (Eval) | WER1.91 | 4 | |
| Voice-cloning intelligibility | Seed-TTS-Eval (zh-hard) | WER5.83 | 4 |
Showing 25 of 30 rows