Fact · Speech recognition
23times
On the Open ASR Leaderboard, Parakeet TDT 0.6B v2 processes audio about 23 times faster than Whisper Large v3 (RTFx 3,390 against 146).
Checked against its source on October 16, 2026
- How it is calculated
- 3390 / 146 = 23.2
Calculated from
- On the Open ASR Leaderboard's English short-form track, NVIDIA Parakeet TDT 0.6B v2 had an average word error rate of 6.05 percent and an inverse real-time factor of 3,390.
- On the same leaderboard track, OpenAI Whisper Large v3 had an average word error rate of 7.44 percent and an inverse real-time factor of 146.