Multi-speaker Transcription on AliMeeting Chinese
10.92DERVIBEVOICE-ASR
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| VIBEVOICE-ASRInference Protocol=Single-pass2026.01 | 10.92 | 29.33 | 29.51 | 27.4 | |
| Gemini-2.5-ProInference Protocol=Chunk-wise, Chunk Duration=240s2026.01 | 31.6 | 41.64 | 53.49 | 27.43 | |
| Gemini-3-ProInference Protocol=Chunk-wise, Chunk Duration=240s2026.01 | 38.75 | 32.84 | 65.61 | 26.75 |