{"id":"nvidia-nemotron-speech-streaming-en-0-6b","nom":"Nemotron ASR Streaming","editeur":"NVIDIA","pays":"États-Unis","poids_ouverts":true,"poids_selon":null,"licence":"NVIDIA Open Model License","licence_selon":null,"liens":{"page":"https://huggingface.co/nvidia/nemotron-speech-streaming-en-0.6b","essayer":"https://build.nvidia.com/nvidia/nemotron-asr-streaming"},"fiche_auto":false,"page":"https://quelleia.com/voix/modeles/nvidia-nemotron-speech-streaming-en-0-6b/","releve":"2026-10-19","en_bref":"32e sur 53 en transcription en anglais (Open ASR).","presentation":"Modèle de transcription anglaise en streaming de NVIDIA, conçu pour les assistants vocaux, le sous-titrage en direct et les agents conversationnels à faible latence. Son encodeur FastConformer à cache traite seulement les nouveaux morceaux d'audio et le texte sort ponctué, avec majuscules.","sortie":"2026-01-05","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"],"lu":"https://huggingface.co/nvidia/nemotron-speech-streaming-en-0.6b/raw/main/README.md (« Nemotron-ASR-Streaming is an English, streaming Automatic Speech Recognition (ASR) »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://huggingface.co/nvidia/nemotron-speech-streaming-en-0.6b/raw/main/README.md (« such as voice assistants, live captioning, and conversational AI systems »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://huggingface.co/nvidia/nemotron-speech-streaming-en-0.6b/raw/main/README.md (« the cache-aware architecture enables continuous transcription by processing only new audio chunks while reusing cached encoder context »), 17/10/2026"},{"appuie":["langues"],"lu":"https://huggingface.co/nvidia/nemotron-speech-streaming-en-0.6b/raw/main/README.md (« This model is for transcription of English audio. »), 17/10/2026"},{"appuie":["sortie"],"lu":"https://huggingface.co/nvidia/nemotron-speech-streaming-en-0.6b/raw/main/README.md (« (older checkpoint [01/05/2026] via https://huggingface.co/nvidia/nemotron-speech-streaming-en-0.6b/tree/nemotron-speech-streaming-jan2026) »), 17/10/2026"},{"appuie":["taille"],"lu":"https://huggingface.co/nvidia/nemotron-speech-streaming-en-0.6b/raw/main/README.md (« Parameters: 600M »), 17/10/2026"},{"appuie":["langues"],"lu":"https://huggingface.co/nvidia/nemotron-3.5-asr-streaming-0.6b/raw/main/README.md (« We would recommend [Nemotron ASR Streaming (English)](https://huggingface.co/nvidia/nemotron-speech-streaming-en-0.6b) model for English-only transcription use cases. »), 17/10/2026"}],"classements":[{"id":"transcription/open-asr-anglais","nom":"Transcription en anglais, Open ASR","rang":32,"sur":53,"valeur":6.6,"unite":"%","chiffres":{"rtfx":1111.45,"jeux":{"AMI-Cleaned":8.84,"Earnings22-Cleaned-AA-chunked":9.45,"Gigaspeech-Cleaned":7.9,"LS Clean":1.89,"LS Other":4.35,"Private (conversational)":13.28,"Private (scripted)":4.79,"SPGISpeech":2.69,"URGENT24":12.54,"Voice Arena Monsoon":4.44,"Voxpopuli-AA-Cleaned":2.4}},"voisins":["ibm-granite-4-0-1b-speech","distil-large-v3-5"],"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":{"hf_audio":"nvidia/nemotron-speech-streaming-en-0.6b"}}