Automatic Speech Recognition on CommonVoice CN
7.29WERS3 Tokenizer(FSQ)
Evaluation results
| Method | Links | |
|---|---|---|
| S3 Tokenizer(FSQ)Codebook Size=6561, FPS=252026.01 | 7.29 | |
| Qwen-TTS-Tokenizer-25Hz (Stage 1)Codebook Size=32768, FPS=252026.01 | 10.73 | |
| Qwen-TTS-Tokenizer-25Hz (Stage 2)Codebook Size=32768, FPS=252026.01 | 14.99 | |
| S3 Tokenizer(VQ)Codebook Size=4096, FPS=502026.01 | 15.38 | |
| S3 Tokenizer(VQ)Codebook Size=4096, FPS=252026.01 | 18.26 |