{
 "edition": "2026-W43",
 "date": "2026-10-19",
 "id": "funaudiollm",
 "nom": "FunAudioLLM",
 "url": "https://quelleia.com/editeurs/funaudiollm/",
 "pays": "Chine",
 "ecritures": [
  "FunAudioLLM"
 ],
 "liens": {
  "site": "https://fun-audio-llm.github.io/",
  "essayer": null,
  "application": null,
  "api": null
 },
 "totaux": {
  "modeles": 2,
  "langage": 0,
  "langage_classes": 0,
  "images": 0,
  "images_classes": 0,
  "videos": 0,
  "videos_classes": 0,
  "decision": 0,
  "voix": 2
 },
 "langage": [],
 "images": [],
 "videos": [],
 "decision": [],
 "voix": [
  {
   "id": "funaudiollm-fun-cosyvoice3-0-5b-2512",
   "nom": "Fun-CosyVoice 3.0",
   "url": "https://quelleia.com/voix/modeles/funaudiollm-fun-cosyvoice3-0-5b-2512/",
   "classements": [
    {
     "id": "synthese/prononciation",
     "rang": 6,
     "sur": 16,
     "valeur": "5,79 %",
     "source": "Source : Open TTS Leaderboard, Hugging Face"
    }
   ]
  },
  {
   "id": "funaudiollm-fun-asr-nano-2512-hf",
   "nom": "Fun-ASR-Nano-2512-hf",
   "url": "https://quelleia.com/voix/modeles/funaudiollm-fun-asr-nano-2512-hf/",
   "classements": [
    {
     "id": "transcription/open-asr-anglais",
     "rang": 37,
     "sur": 53,
     "valeur": "7,24 %",
     "source": "Source : Open ASR Leaderboard, Hugging Face"
    }
   ]
  }
 ],
 "presentation_voix": {
  "texte": "FunAudioLLM réunit les modèles vocaux ouverts de l'équipe voix du Tongyi Lab, chez Alibaba Group, dont la reconnaissance vocale Fun-ASR et SenseVoice et la synthèse vocale CosyVoice. Les modèles sont publiés sur Hugging Face et ModelScope, avec le code sur GitHub.",
  "faits": [
   {
    "nom": "Pays du siège",
    "valeur": "Chine",
    "url": "https://fun-audio-llm.github.io/"
   },
   {
    "nom": "Siège",
    "valeur": "Hangzhou",
    "url": "https://www.sec.gov/Archives/edgar/data/1577552/000119312526231755/baba-20260331.htm"
   }
  ],
  "site": "https://fun-audio-llm.github.io/",
  "pages_lues": [
   "https://fun-audio-llm.github.io/ (« Tongyi SpeechTeam Alibaba Group Abstract: This report introduces FunAudioLLM , a framework designed to enhance natural voice interactions »), 17/10/2026",
   "https://fun-audio-llm.github.io/ (« Tongyi SpeechTeam Alibaba Group Abstract: This report introduces FunAudioLLM , a framework designed to enhance natural voice interactions »), 17/10/2026",
   "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. »), 17/10/2026",
   "https://www.sec.gov/Archives/edgar/data/1577552/000119312526231755/baba-20260331.htm (« The principal executive offices of major businesses within Alibaba Group are located at 960-1 West Wen Yi Road, Yu Hang District, Hangzhou 311121, People’s Republic of China. »), 17/10/2026"
  ]
 },
 "outils_qui_proposent": [],
 "outils_edites": [],
 "en_local": [],
 "voisins": [
  "shanghai-ai-laboratory",
  "baichuan",
  "ant-group",
  "openbmb"
 ]
}