{"as_of":"2026-10-12","license":"CC-BY-4.0","license_url":"https://creativecommons.org/licenses/by/4.0/","cite_as":"The Local Bench (thelocalbench.com), data as of 2026-10-12, CC BY 4.0","source_url":"https://thelocalbench.com","category":"stt","slug":"speech-to-text","label":"Speech to text","bench":"Open ASR Leaderboard, average WER (English short-form)","unit":"% WER","higher":false,"src":"hf-audio/open-asr-leaderboard-results, english_short_latest.csv (leaderboard version 09-10-2026)","url":"https://huggingface.co/spaces/hf-audio/open_asr_leaderboard","groups":[{"label":"Open ASR Leaderboard, average WER (English short-form)","ranked":[{"rank":1,"id":"canary-qwen-2-5b","name":"Canary-Qwen 2.5B","hf_repo":"nvidia/canary-qwen-2.5b","score":{"bench":"Open ASR Leaderboard, average WER (English short-form)","value":6.37,"unit":"% WER","flag":"sourced","source":"https://huggingface.co/datasets/hf-audio/open-asr-leaderboard-results/blob/d3c0e9a07b475a64afb56254e8c35b584905af32/english_short_latest.csv","note":"avg 6.3686, RTFx 881.67."}},{"rank":2,"id":"parakeet-tdt-0-6b-v2","name":"Parakeet TDT 0.6B v2","hf_repo":"nvidia/parakeet-tdt-0.6b-v2","score":{"bench":"Open ASR Leaderboard, average WER (English short-form)","value":6.43,"unit":"% WER","flag":"sourced","source":"https://huggingface.co/datasets/hf-audio/open-asr-leaderboard-results/blob/d3c0e9a07b475a64afb56254e8c35b584905af32/english_short_latest.csv","note":"avg 6.4329, RTFx 6148.32."}},{"rank":3,"id":"parakeet-tdt-0-6b-v3","name":"Parakeet TDT 0.6B v3","hf_repo":"nvidia/parakeet-tdt-0.6b-v3","score":{"bench":"Open ASR Leaderboard, average WER (English short-form)","value":6.51,"unit":"% WER","flag":"sourced","source":"https://huggingface.co/datasets/hf-audio/open-asr-leaderboard-results/blob/d3c0e9a07b475a64afb56254e8c35b584905af32/english_short_latest.csv","note":"avg 6.5143, RTFx 6227.73."}},{"rank":4,"id":"distil-large-v3-5","name":"Distil-Whisper large-v3.5","hf_repo":"distil-whisper/distil-large-v3.5","score":{"bench":"Open ASR Leaderboard, average WER (English short-form)","value":7.02,"unit":"% WER","flag":"sourced","source":"https://huggingface.co/datasets/hf-audio/open-asr-leaderboard-results/blob/d3c0e9a07b475a64afb56254e8c35b584905af32/english_short_latest.csv","note":"avg 7.0229, RTFx 898.21."}},{"rank":5,"id":"voxtral-mini-3b-2507","name":"Voxtral Mini 3B","hf_repo":"mistralai/Voxtral-Mini-3B-2507","score":{"bench":"Open ASR Leaderboard, average WER (English short-form)","value":7.84,"unit":"% WER","flag":"sourced","source":"https://huggingface.co/datasets/hf-audio/open-asr-leaderboard-results/blob/d3c0e9a07b475a64afb56254e8c35b584905af32/english_short_latest.csv","note":"avg 7.8371, RTFx 179.78."}},{"rank":6,"id":"whisper-large-v3","name":"Whisper large-v3","hf_repo":"openai/whisper-large-v3","score":{"bench":"Open ASR Leaderboard, average WER (English short-form)","value":7.84,"unit":"% WER","flag":"sourced","source":"https://huggingface.co/datasets/hf-audio/open-asr-leaderboard-results/blob/d3c0e9a07b475a64afb56254e8c35b584905af32/english_short_latest.csv","note":"avg 7.8414, RTFx 470.73."}},{"rank":7,"id":"whisper-large-v3-turbo","name":"Whisper large-v3 turbo","hf_repo":"openai/whisper-large-v3-turbo","score":{"bench":"Open ASR Leaderboard, average WER (English short-form)","value":8.39,"unit":"% WER","flag":"sourced","source":"https://huggingface.co/datasets/hf-audio/open-asr-leaderboard-results/blob/d3c0e9a07b475a64afb56254e8c35b584905af32/english_short_latest.csv","note":"avg 8.3871, RTFx 810.5."}}],"not_yet_measured":[{"id":"canary-1b-flash","name":"Canary 1B Flash","hf_repo":"nvidia/canary-1b-flash"}]}]}