{"id":"openai-whisper-large-v2","nom":"Whisper Large v2","editeur":"OpenAI","pays":"États-Unis","poids_ouverts":true,"poids_selon":null,"licence":"Apache 2.0","licence_selon":null,"liens":{"page":"https://huggingface.co/openai/whisper-large-v2"},"fiche_auto":true,"page":"https://quelleia.com/voix/modeles/openai-whisper-large-v2/","releve":"2026-10-19","en_bref":"29e sur 51 en transcription en anglais (Artificial Analysis).","presentation":"Deuxième version du grand modèle Whisper d'OpenAI, pour la transcription multilingue et la traduction de la parole vers l'anglais, publiée avec ses poids. Même architecture que le modèle large d'origine, entraînée 2,5 fois plus longtemps avec davantage de régularisation.","sortie":"2022-12-08","taille":"1,55 milliard de paramètres","langues":{"annoncees":{"annoncees":"99 langues, dont le français","nombre":99,"francais":true},"prises_en_charge_selon_open_tts":null,"evaluees":["en"]},"preuves":[{"appuie":["sortie"],"lu":"https://github.com/openai/whisper/discussions/661 (« jongwook Dec 8, 2022 Maintainer We are pleased to announce the large-v2 model. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://huggingface.co/openai/whisper-large-v2/raw/main/README.md (« Compared to the Whisper large model, the large-v2 model is trained for 2.5x more epochs with added regularization »), 17/10/2026"},{"appuie":["taille"],"lu":"https://huggingface.co/openai/whisper-large-v2/raw/main/README.md (« | large-v2 | 1550 M »), 17/10/2026"},{"appuie":["langues"],"lu":"https://huggingface.co/openai/whisper-large-v2/raw/main/README.md (« language: - en - zh - de - es - ru - ko - fr »), 17/10/2026"},{"appuie":["langues"],"lu":"https://huggingface.co/openai/whisper-large-v2 (« Safetensors 99 languages whisper audio hf-asr-leaderboard Eval Results arxiv: 2212.04356 License: apache-2.0 »), 17/10/2026"}],"classements":[{"id":"transcription/artificial-analysis","nom":"Transcription en anglais, indice AA-WER","rang":29,"sur":51,"valeur":4.06,"unite":"%","chiffres":{"prix_pour_1000_minutes":6,"jeux":{"AA-AgentTalk":3.19,"Earnings22":7.04,"VoxPopuli":2.81},"date_sortie":"2022-12-08","hebergeur":"OpenAI"},"voisins":["speechmatics-enhanced","solaria-1"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/speech-to-text/models/whisper","releve":"2026-10-19"}}],"noms_dans_les_sources":{"artificial_analysis":"Whisper Large v2"}}