{"id":"edge0-audio8-asr-0-1b","nom":"Audio8-ASR-0.1B","editeur":"Edge0","pays":null,"poids_ouverts":true,"poids_selon":null,"licence":"CC BY-NC 4.0","licence_selon":null,"liens":{"page":"https://edge0.ai/models/asr-0.1b","essayer":"https://huggingface.co/spaces/Edge0/audio8-asr-0-1b"},"fiche_auto":true,"page":"https://quelleia.com/voix/modeles/edge0-audio8-asr-0-1b/","releve":"2026-10-19","en_bref":"45e sur 53 en transcription en anglais (Open ASR).","presentation":"Petit modèle de transcription multilingue conçu pour fonctionner entièrement sur l'appareil (téléphone, objet connecté), avec des versions ONNX Runtime et Apple Neural Engine. Son modèle de langage ne compte qu'environ 0,1 milliard de paramètres et l'audio ne quitte pas l'appareil.","sortie":"2026-09-10","taille":"environ 0,1 milliard de paramètres pour le modèle de langage, 0,32 milliard au total","langues":{"annoncees":{"annoncees":"7 langues, dont le français et le cantonais","nombre":7,"francais":true,"liste":["zh","en","fr","de","ja","ko"]},"prises_en_charge_selon_open_tts":null,"evaluees":["en"]},"preuves":[{"appuie":["langues","presentation","taille"],"lu":"https://huggingface.co/Edge0/Audio8-ASR-0.1B/raw/main/README.md (« is a compact autoregressive ASR model whose language-model component has only 0.1B parameters. It supports multilingual speech recognition for languages including Chinese, English, French, German, Japanese, Korean, and Cantonese. »), 17/10/2026"},{"appuie":["taille"],"lu":"https://huggingface.co/Edge0/Audio8-ASR-0.1B/raw/main/README.md (« 323,990,528 (about 0.324B) »), 17/10/2026"},{"appuie":["langues"],"lu":"https://edge0.ai/models/asr-0.1b (« Runtime CPU / edge / mobile / Apple ANE Languages 7 »), 17/10/2026"},{"appuie":["sortie"],"lu":"https://edge0.ai/models/asr-0.1b (« Audio8 · ASR · 0.1B September 10, 2026 »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://edge0.ai/models/asr-0.1b (« Audio8 ASR 0.1B brings practical automatic speech recognition to phones, wearables, recorders and other constrained hardware. »), 17/10/2026"}],"classements":[{"id":"transcription/open-asr-anglais","nom":"Transcription en anglais, Open ASR","rang":45,"sur":53,"valeur":8.29,"unite":"%","chiffres":{"rtfx":718.79,"jeux":{"AMI-Cleaned":11,"Earnings22-Cleaned-AA-chunked":12.53,"Gigaspeech-Cleaned":8.48,"LS Clean":2.71,"LS Other":6.6,"Private (conversational)":14.79,"Private (scripted)":5.85,"SPGISpeech":3.73,"URGENT24":14.97,"Voice Arena Monsoon":6.18,"Voxpopuli-AA-Cleaned":4.39}},"voisins":["microsoft-vibevoice-asr-hf","voxtral-mini-4b-realtime"],"source":{"nom":"Open ASR Leaderboard","mention":"Source : Open ASR Leaderboard, Hugging Face","url":"https://huggingface.co/spaces/hf-audio/open_asr_leaderboard","releve":"2026-10-19"}}],"noms_dans_les_sources":{"hf_audio":"Edge0/Audio8-ASR-0.1B"}}