{"id":"funaudiollm-fun-asr-nano-2512-hf","nom":"Fun-ASR-Nano-2512-hf","editeur":"FunAudioLLM","pays":"Chine","poids_ouverts":true,"poids_selon":null,"licence":"Apache 2.0","licence_selon":null,"liens":{"page":"https://github.com/FunAudioLLM/Fun-ASR","essayer":"https://huggingface.co/spaces/FunAudioLLM/Fun-ASR-Nano"},"fiche_auto":true,"page":"https://quelleia.com/voix/modeles/funaudiollm-fun-asr-nano-2512-hf/","releve":"2026-10-19","en_bref":"37e sur 53 en transcription en anglais (Open ASR).","presentation":"Fun-ASR-Nano est un modèle de reconnaissance vocale de bout en bout du Tongyi Lab, entraîné sur des dizaines de millions d'heures de parole réelle. Cette version au format Hugging Face Transformers couvre le chinois (sept groupes dialectaux et 26 accents régionaux), l'anglais et le japonais.","taille":"800 millions de paramètres","langues":{"annoncees":{"annoncees":"3 langues (chinois, anglais, japonais)","nombre":3,"francais":false,"liste":["zh","en","ja"]},"prises_en_charge_selon_open_tts":null,"evaluees":["en"]},"preuves":[{"appuie":["langues","presentation"],"lu":"https://huggingface.co/FunAudioLLM/Fun-ASR-Nano-2512-hf/raw/main/README.md (« This checkpoint supports Chinese, English, and Japanese; its Chinese coverage includes 7 dialect groups and 26 regional accents. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://huggingface.co/FunAudioLLM/Fun-ASR-Nano-2512/raw/main/README.md (« Fun-ASR is an end-to-end speech recognition large model launched by Tongyi Lab. It is trained on tens of millions of hours of real speech data »), 17/10/2026"},{"appuie":["taille"],"lu":"https://huggingface.co/FunAudioLLM/Fun-ASR-Nano-2512/raw/main/README.md (« | Tens of millions of hours | 800M | »), 17/10/2026"}],"classements":[{"id":"transcription/open-asr-anglais","nom":"Transcription en anglais, Open ASR","rang":37,"sur":53,"valeur":7.24,"unite":"%","chiffres":{"rtfx":495.85,"jeux":{"AMI-Cleaned":10.35,"Earnings22-Cleaned-AA-chunked":10.87,"Gigaspeech-Cleaned":8.41,"LS Clean":1.47,"LS Other":4.07,"Private (conversational)":14.83,"Private (scripted)":4.95,"SPGISpeech":2.05,"URGENT24":13.93,"Voice Arena Monsoon":5.32,"Voxpopuli-AA-Cleaned":3.4}},"voisins":["whisper-large-v3","voxtral-mini"],"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":"FunAudioLLM/Fun-ASR-Nano-2512-hf"}}