{"id":"meta-omniasr-ctc-7b-v2","nom":"omniASR-CTC-7B-v2","editeur":"Meta","pays":"États-Unis","poids_ouverts":true,"poids_selon":null,"licence":"Apache 2.0","licence_selon":null,"liens":{"page":"https://github.com/facebookresearch/omnilingual-asr"},"fiche_auto":true,"page":"https://quelleia.com/voix/modeles/meta-omniasr-ctc-7b-v2/","releve":"2026-10-19","en_bref":"29e sur 39 en transcription en français ; 50e sur 53 en transcription en anglais (Open ASR).","presentation":"Modèle ouvert de reconnaissance vocale de la famille Omnilingual ASR de Meta, version v2 de décembre 2025 à décodage CTC. Elle transcrit l'audio sans décodeur de type LLM, et la famille couvre plus de 1600 langues.","sortie":"2025-12","taille":"6,5 milliards de paramètres","langues":{"annoncees":{"annoncees":"plus de 1600 langues, dont le français","nombre":1600,"plus":true,"francais":true},"prises_en_charge_selon_open_tts":null,"evaluees":["fr","en"]},"preuves":[{"appuie":["sortie"],"lu":"https://raw.githubusercontent.com/facebookresearch/omnilingual-asr/main/README.md (« ## December 2025 Update »), 17/10/2026"},{"appuie":["presentation","sortie"],"lu":"https://raw.githubusercontent.com/facebookresearch/omnilingual-asr/main/README.md (« We release two suites of models: - Checkpoints of improved accuracy (CER) for the CTC and LLM-ASR models compared to our existing LLM-ASR model (`omniASR_{CTC,LLM}_{300M,1B,3B,7B}_v2`). »), 17/10/2026"},{"appuie":["langues","presentation"],"lu":"https://raw.githubusercontent.com/facebookresearch/omnilingual-asr/main/README.md (« Omnilingual ASR is an open-source speech recognition system supporting over 1,600 languages »), 17/10/2026"},{"appuie":["langues"],"lu":"https://raw.githubusercontent.com/facebookresearch/omnilingual-asr/main/per_language_results_table_7B_llm_asr.csv (« fra_Latn,4615.1,2.2 »), 17/10/2026"},{"appuie":["presentation","taille"],"lu":"https://raw.githubusercontent.com/facebookresearch/omnilingual-asr/main/README.md (« | [`omniASR_CTC_7B_v2`](https://dl.fbaipublicfiles.com/mms/omniASR-CTC-7B-v2.pt) | ASR | 6_504_786_132 | »), 17/10/2026"}],"classements":[{"id":"transcription/francais","nom":"Transcription en français","rang":29,"sur":39,"valeur":7.57,"unite":"%","chiffres":{"rtfx":332.74,"jeux":{"Common Voice":10.12,"FLEURS":7.65,"MLS":4.94}},"voisins":["meta-omniasr-llm-1b-v2","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"}},{"id":"transcription/open-asr-anglais","nom":"Transcription en anglais, Open ASR","rang":50,"sur":53,"valeur":11.5,"unite":"%","chiffres":{"rtfx":518.64,"jeux":{"AMI-Cleaned":17.44,"Earnings22-Cleaned-AA-chunked":18.3,"Gigaspeech-Cleaned":12.95,"LS Clean":2.12,"LS Other":5.05,"Private (conversational)":20.62,"Private (scripted)":14.66,"SPGISpeech":5.16,"URGENT24":18.68,"Voice Arena Monsoon":7.08,"Voxpopuli-AA-Cleaned":4.43}},"voisins":["abr-ai-niagara-38m-batch-en","google-gemma-4-e4b-it"],"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":"facebook/omniASR-CTC-7B-v2"}}