{"id":"fun-audio-chat-8b","nom":"Fun-Audio-Chat-8B","editeur":"FunAudioLLM","pays":"Chine","page":"https://quelleia.com/voix/modeles/fun-audio-chat-8b/","domaine":"voix-a-voix","annonce_le":"2025-12-23","en_attente":true,"mesure":null,"classe":false,"note":"pas encore mesuré par une source publique ; aucun rang, aucun chiffre de classement","classements":[],"poids_ouverts":true,"licence":"Apache 2.0","liens":{"poids":"https://huggingface.co/FunAudioLLM/Fun-Audio-Chat-8B","page":"https://huggingface.co/FunAudioLLM/Fun-Audio-Chat-8B"},"presentation":"Grand modèle audio à poids ouverts de FunAudioLLM, conçu pour des conversations vocales naturelles à faible latence, qui répond à la voix par la voix en anglais et en chinois. Il sait aussi comprendre un enregistrement, suivre des consignes de style oral et appeler des fonctions à partir de la parole.","sortie":"2025-12-23","taille":"8 milliards de paramètres environ","langues":{"annoncees":{"annoncees":"anglais et chinois","nombre":2,"francais":false,"liste":["en","zh"]}},"annonce_de_l_editeur":null,"preuves":[{"appuie":["presentation"],"lu":"https://huggingface.co/FunAudioLLM/Fun-Audio-Chat-8B/raw/main/README.md (« **Fun-Audio-Chat** is a Large Audio Language Model built for natural, low-latency voice interactions. »), 23/10/2026"},{"appuie":["presentation"],"lu":"https://huggingface.co/FunAudioLLM/Fun-Audio-Chat-8B/raw/main/README.md (« - **Comprehensive Capabilities**: Supports spoken QA, audio understanding, speech function calling, speech instruction-following, voice empathy »), 23/10/2026"},{"appuie":["presentation"],"lu":"https://huggingface.co/FunAudioLLM/Fun-Audio-Chat-8B/raw/main/README.md (« # Speech-to-Speech »), 23/10/2026"},{"appuie":["taille"],"lu":"https://huggingface.co/FunAudioLLM/Fun-Audio-Chat-8B/raw/main/README.md (« | Model Size | ~8B parameters | »), 23/10/2026"},{"appuie":["langues"],"lu":"https://huggingface.co/FunAudioLLM/Fun-Audio-Chat-8B/raw/main/README.md (« | Languages | English, Chinese | »), 23/10/2026"},{"appuie":["sortie"],"lu":"https://raw.githubusercontent.com/FunAudioLLM/Fun-Audio-Chat/main/README.md (« - **[2025.12.23]** Fun-Audio-Chat-8B (model, training and inference code) released with state-of-the-art performance on multiple spoken question answering, audio understanding, speech function calling, speech instruction-following and voice empathy benchmarks »), 23/10/2026"}]}