{
 "edition": "2026-W43",
 "date": "2026-10-19",
 "id": "next-gen-kaldi",
 "nom": "Next-gen Kaldi",
 "url": "https://quelleia.com/editeurs/next-gen-kaldi/",
 "pays": null,
 "ecritures": [
  "Next-gen Kaldi"
 ],
 "liens": {
  "site": "https://k2-fsa.org/",
  "essayer": null,
  "application": null,
  "api": null
 },
 "totaux": {
  "modeles": 1,
  "langage": 0,
  "langage_classes": 0,
  "images": 0,
  "images_classes": 0,
  "videos": 0,
  "videos_classes": 0,
  "decision": 0,
  "voix": 1
 },
 "langage": [],
 "images": [],
 "videos": [],
 "decision": [],
 "voix": [
  {
   "id": "k2-fsa-omnivoice",
   "nom": "OmniVoice",
   "url": "https://quelleia.com/voix/modeles/k2-fsa-omnivoice/",
   "classements": [
    {
     "id": "synthese/prononciation",
     "rang": 1,
     "sur": 16,
     "valeur": "4,72 %",
     "source": "Source : Open TTS Leaderboard, Hugging Face"
    }
   ]
  }
 ],
 "presentation_voix": {
  "texte": "Next-gen Kaldi (organisation GitHub k2-fsa) est un projet open source d'outils de reconnaissance vocale, avec les bibliothèques k2, icefall, lhotse et sherpa. Il publie aussi des modèles de synthèse vocale, dont OmniVoice.",
  "faits": [],
  "site": "https://k2-fsa.org/",
  "pages_lues": [
   "https://k2-fsa.org/ (« Next-gen Kaldi for advanced & efficient automatic speech recognition A collection of automatic recognition toolkits consisting of data preparation, sequence modeling, training, decoding, deploying. »), 17/10/2026",
   "https://k2-fsa.org/ (« Copyright © 2019 - 2024 Next-gen Kaldi team »), 17/10/2026"
  ]
 },
 "outils_qui_proposent": [],
 "outils_edites": [],
 "en_local": [],
 "voisins": [
  "shanghai-ai-laboratory",
  "elevenlabs",
  "fish-audio",
  "hugging-face"
 ]
}