{"id":"parakeet-tdt-0-6b-v2","nom":"Parakeet TDT 0.6B V2","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-tdt-0.6b-v2","essayer":"https://huggingface.co/spaces/nvidia/parakeet-tdt-0.6b-v2"},"fiche_auto":false,"page":"https://quelleia.com/voix/modeles/parakeet-tdt-0-6b-v2/","releve":"2026-10-19","en_bref":"48e sur 51 en transcription en anglais (Artificial Analysis) ; 21e sur 53 en transcription en anglais (Open ASR).","presentation":"Modèle de transcription anglaise de NVIDIA avec ponctuation, majuscules et horodatage au mot, fondé sur un encodeur FastConformer et un décodeur TDT. Il traite jusqu'à 24 minutes d'audio d'un seul passage.","sortie":"2025-05-01","taille":"600 millions 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","taille"],"lu":"https://huggingface.co/nvidia/parakeet-tdt-0.6b-v2/raw/main/README.md (« is a 600-million-parameter automatic speech recognition (ASR) model designed for high-quality English transcription, featuring support for punctuation, capitalization, and accurate timestamp prediction »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://huggingface.co/nvidia/parakeet-tdt-0.6b-v2/raw/main/README.md (« This XL variant of the FastConformer [1] architecture integrates the TDT [2] decoder and is trained with full attention, enabling efficient transcription of audio segments up to 24 minutes in a single pass. »), 17/10/2026"},{"appuie":["sortie"],"lu":"https://huggingface.co/nvidia/parakeet-tdt-0.6b-v2/raw/main/README.md (« Release Date: 05/01/2025 »), 17/10/2026"}],"classements":[{"id":"transcription/artificial-analysis","nom":"Transcription en anglais, indice AA-WER","rang":48,"sur":51,"valeur":6.43,"unite":"%","chiffres":{"prix_pour_1000_minutes":0,"jeux":{"AA-AgentTalk":5.84,"Earnings22":9.42,"VoxPopuli":4.6},"date_sortie":"2025-05-01","hebergeur":"NVIDIA"},"voisins":["rev-ai","gradium-speech-to-text"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/speech-to-text/models/nvidia","releve":"2026-10-19"}},{"id":"transcription/open-asr-anglais","nom":"Transcription en anglais, Open ASR","rang":21,"sur":53,"valeur":5.98,"unite":"%","chiffres":{"rtfx":14156.47,"jeux":{"AMI-Cleaned":9.02,"Earnings22-Cleaned-AA-chunked":6.83,"Gigaspeech-Cleaned":8.17,"LS Clean":1.27,"LS Other":2.65,"Private (conversational)":13.33,"Private (scripted)":3.48,"SPGISpeech":1.87,"URGENT24":11.58,"Voice Arena Monsoon":3.7,"Voxpopuli-AA-Cleaned":3.89}},"voisins":["ibm-granite-speech-4-1-2b","solaria-3"],"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":{"artificial_analysis":"Parakeet TDT 0.6B V2","hf_audio":"nvidia/parakeet-tdt-0.6b-v2"}}