{"id":"nvidia-parakeet-rnnt-1-1b","nom":"Parakeet RNNT 1.1B","editeur":"NVIDIA","pays":"États-Unis","poids_ouverts":true,"poids_selon":null,"licence":"CC BY 4.0","licence_selon":null,"liens":{"page":"https://huggingface.co/nvidia/parakeet-rnnt-1.1b"},"fiche_auto":true,"page":"https://quelleia.com/voix/modeles/nvidia-parakeet-rnnt-1-1b/","releve":"2026-10-19","en_bref":"46e sur 51 en transcription en anglais (Artificial Analysis).","presentation":"Modèle de transcription anglaise de NVIDIA, développé avec Suno.ai, fondé sur un encodeur FastConformer de taille XXL et un décodeur transducteur (RNNT). Il transcrit l'anglais en alphabet minuscule.","taille":"environ 1,1 milliard de paramètres","langues":{"annoncees":{"annoncees":"anglais seulement","nombre":1,"francais":false,"liste":["en"]},"prises_en_charge_selon_open_tts":null,"evaluees":["en"]},"preuves":[{"appuie":["langues","presentation"],"lu":"https://huggingface.co/nvidia/parakeet-rnnt-1.1b/raw/main/README.md (« is an ASR model that transcribes speech in lower case English alphabet. This model is jointly developed by [NVIDIA NeMo](https://github.com/NVIDIA/NeMo) and [Suno.ai](https://www.suno.ai/) teams. »), 17/10/2026"},{"appuie":["presentation","taille"],"lu":"https://huggingface.co/nvidia/parakeet-rnnt-1.1b/raw/main/README.md (« It is an XXL version of FastConformer Transducer [1] (around 1.1B parameters) model. »), 17/10/2026"}],"classements":[{"id":"transcription/artificial-analysis","nom":"Transcription en anglais, indice AA-WER","rang":46,"sur":51,"valeur":5.42,"unite":"%","chiffres":{"prix_pour_1000_minutes":1.91,"jeux":{"AA-AgentTalk":4.37,"Earnings22":9,"VoxPopuli":3.96},"date_sortie":"2024-01-01","hebergeur":"Replicate"},"voisins":["deepgram-nova-3","rev-ai"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/speech-to-text/models/nvidia","releve":"2026-10-19"}}],"noms_dans_les_sources":{"artificial_analysis":"Parakeet RNNT 1.1B"}}