Updated daily at 05:00 UTC
Benchmark
Open ASR Leaderboard
Measures: Speech-to-text models transcribe English short-form test sets (AMI, Earnings22, Gigaspeech, LibriSpeech clean and other, SPGISpeech, VoxPopuli, Voice Arena, plus private sets) through one shared normalizer; ranked by average word error rate, with inverse real-time factor (RTFx) for speed. Separate multilingual and long-form tracks.
- Maintainer
- Hugging Face (hf-audio)
- Introduced
- —
- Status
- Active
- Saturation
- Near-ceiling
- Typical provenance
- Independent
- In scoring set
- Yes
Leaderboard
Independent and third-party results only.
No independent or third-party results yet. Show all results