Fact · Speech recognition
7.44percent average WER
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.
Checked against its source on October 16, 2026
In the source's own words
“OpenAI Whisper Large v3 Yes 7.44 146 Whisper”
Open ASR Leaderboard: Towards Reproducible and Transparent Multilingual and Long-Form Speech Recognition Evaluation, Hugging Face and collaborators, arXiv, 2025, Table 3.
Open the original- What it measures
- Whisper supports 99 languages, which the fastest English models do not.
- What it does not show
- Same leaderboard conditions as the Parakeet figure; speeds on other hardware differ.
Source
Used to calculate
- On the Open ASR Leaderboard's English short-form tests, the average word error rate of Canary-Qwen 2.5B was about 24 percent lower than that of Whisper Large v3.
- An inverse real-time factor of 146 means the leaderboard engine processes about 146 seconds of audio for each second of compute, so one hour of audio takes about 25 seconds of compute time.
- 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).
Cited on
- Speech Recognition: What It Is and How Well It WorksTopic
- What Is Whisper AI? OpenAI's Speech Model ExplainedGuide
- Speech-to-Text APIs Compared: Price, Accuracy, SpeedGuide
- Word Error Rate (WER): How to Calculate and Read ItGuide
- Speech to Text and LLMs: What Language Models ChangeGuide
- Speech Recognition Models: How Neural ASR WorksGuide
- Human vs AI Transcription: Accuracy, Cost, SpeedGuide
- Open-Source Speech Recognition: The Best ModelsGuide
- Speech to Text on Linux: Dictation on Ubuntu and MintGuide
- Speech Recognition Benchmarks and LeaderboardsGuide
- Transcription Jobs: Pay, Skills and Getting StartedGuide
- Offline Speech to Text on Windows: What WorksGuide
- Real-Time Speech Recognition: Streaming and LatencyGuide
- On-Device vs Cloud Speech Recognition: The TradeoffsGuide
- Can Whisper transcribe in real time?Question
- How do you use Whisper for dictation on Linux?Question
- How long does it take to transcribe one hour of audio?Question
- Is ElevenLabs speech to text better than Whisper?Question
- What are the best alternatives to Whisper?Question
- What are the best Whisper settings for accuracy?Question
- What is NVIDIA Parakeet, and is it better than Whisper?Question
- What is the best speech to text software for Linux?Question
- Which neural network is best for speech recognition?Question
- Which speech-to-text API is the best?Question