Automatic Speech Recognition on CMV zh
6.5WERE2E-TTS-Stage2
Evaluation results
| Method | Links | |
|---|---|---|
| E2E-TTS-Stage2Training Stage=22026.06 | 6.5 | |
| E2E-TTS-Stage1Training Stage=12026.06 | 6.85 | |
| w/o LLMAblation=Without LLM2026.06 | 7.16 | |
| S3-Tokenizer-FSQ2026.06 | 7.27 | |
| w/o LLM and LFMAblation=Without LLM and LFM2026.06 | 7.69 | |
| SenseVoice-small2026.06 | 10.78 | |
| Whisper-large-V32026.06 | 12.4 | |
| Qwen-TTS-Tokenizer2026.06 | 14.99 |