Benchmark Leaderboards
Loading leaderboardsβ¦
Loading leaderboardsβ¦
Track which models hold the current SOTA on the benchmarks the field actually uses. Click a column header to sort; the leading row is highlighted.
Open ASR Leaderboard's main English benchmark β Average WER across 8 standard test sets (AMI, Earnings22, Gigaspeech, LibriSpeech Clean/Other, SPGISpeech, TED-LIUM, Voxpopuli). Lower is better. The community standard for ASR model comparison.
Metric: Average WER β lower is better Β· Source β