Automatic Speech Recognition on Persian (test)
17.1WERCP2
Evaluation results
| Method | Links | |
|---|---|---|
| CP2Initialization=W2V Large init., Number of Parameters=300M, Fine-tuning=on labeled data2025.12 | 17.1 | |
| Whisper Large v3Number of Parameters=1.5B, Fine-tuning=on labeled data2025.12 | 21.4 | |
| CP1Initialization=XLS-R init., Number of Parameters=300M, Fine-tuning=on labeled data2025.12 | 22.3 | |
| CSInitialization=from scratch, Number of Parameters=95M, Fine-tuning=on labeled data2025.12 | 25.4 | |
| W2V LargeNumber of Parameters=300M, Fine-tuning=on labeled data2025.12 | 33.2 | |
| Seamless Large v2Number of Parameters=2.3B, Fine-tuning=on labeled data2025.12 | 41.1 |