Model results

Open ASR Leaderboard

Choose a shared evaluation protocol to compare model scores. Versions, sources and configurations stay separate.

Atlas snapshot captured 10/19/2026, 10:20:28 AM UTC. This is an import timestamp, not the evaluation date. Coverage may be incomplete.

Official source

← All evaluation groups

open-asr-leaderboard · mean wer

Source: Hugging Face eval result
Version: Not reported
Measurement date: 2026-09-22
Metric: % · Lower is better
Evaluation scope: Registered model evaluation · dataset hf-audio/open-asr-leaderboard · task mean_wer · moondream · Publisher self-report through Photon using Open ASR normalizers as of September 2026. Mean WER across eight test sets, including eleven complete TED-LIUM 3 talks substituted for the unavailable leaderboard TED-LIUM split; not the model card’s seven-set Open ASR mean.

Positions are withheld because at least one result lacks explicit independent provenance or a documented evaluation scope. Missing metadata is shown as unreported; matching imported metadata is not independent verification of the protocol.

Parakeet Ultra
moondream/parakeet-ultra
5.32%
View modelEvidence model-card-reported