best model by language
Benchmarked on the FLEURS test split at Q8_0. Error is WER — lower is better. Speed is × realtime on Handy target hardware.
accuracy vs speed
Turkish · 11 models
AMD Ryzen 4750U GPU (Vulkan)
pareto frontier (no model is both faster and more accurate) other models
highlighted rows are recommended picks or on pareto frontier
| | | | | | |
| 1 | whisper-large-v3 | 6.51 | 2.0× | 1.0× | 1.55 GB | Apache-2.0 |
| 2 | whisper-large-v3-turboaccurate pick | 6.97 | 3.1× | 1.4× | 0.83 GB | Apache-2.0 |
| 3 | whisper-large-v2 | 7.63 | 2.0× | 1.0× | 1.55 GB | Apache-2.0 |
| 4 | whisper-large | 8.73 | 2.0× | 1.0× | 1.55 GB | Apache-2.0 |
| 5 | whisper-medium | 9.35 | 4.1× | 1.9× | 0.77 GB | Apache-2.0 |
| 6 | Qwen3-ASR-1.7B | 9.46 | 4.1× | 2.5× | 2.04 GB | Apache-2.0 |
| 7 | nemotron-3.5-asr-streaming-0.6boverall pickfast pick | 15.40 | 17.1× | 10.6× | 0.70 GB | OpenMDW-1.1 |
| 8 | whisper-small | 15.95 | 11.7× | 5.9× | 0.25 GB | Apache-2.0 |
| 9 | Qwen3-ASR-0.6B | 16.74 | 9.7× | 5.3× | 0.79 GB | Apache-2.0 |
| 10 | whisper-base | 31.09 | 29.0× | 19.3× | 0.08 GB | Apache-2.0 |
| 11 | whisper-tiny | 47.98 | 43.1× | 39.8× | 0.04 GB | Apache-2.0 |