{"id":"microsoft-vibevoice-asr-hf","nom":"VibeVoice-ASR-HF","editeur":"Microsoft","pays":"États-Unis","poids_ouverts":true,"poids_selon":null,"licence":"MIT","licence_selon":null,"liens":{"page":"https://huggingface.co/microsoft/VibeVoice-ASR-HF"},"fiche_auto":true,"page":"https://quelleia.com/voix/modeles/microsoft-vibevoice-asr-hf/","releve":"2026-10-19","en_bref":"38e sur 39 en transcription en français ; 44e sur 53 en transcription en anglais (Open ASR).","presentation":"Version compatible Transformers de VibeVoice-ASR, modèle ouvert de transcription de Microsoft qui traite jusqu'à 60 minutes d'audio en une passe. Il produit une transcription structurée (qui parle, quand, quoi) et accepte des mots-clés personnalisés.","sortie":"2026-03-06","langues":{"annoncees":{"annoncees":"plus de 50 langues, dont le français","nombre":50,"plus":true,"francais":true},"prises_en_charge_selon_open_tts":null,"evaluees":["fr","en"]},"preuves":[{"appuie":["presentation"],"lu":"https://huggingface.co/microsoft/VibeVoice-ASR-HF/raw/main/README.md (« **VibeVoice-ASR** is a unified speech-to-text model designed to handle **60-minute long-form audio** in a single pass, generating structured transcriptions containing **Who (Speaker), When (Timestamps), and What (Content)** »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://huggingface.co/microsoft/VibeVoice-ASR-HF/raw/main/README.md (« Users can provide customized hotwords (e.g., specific names, technical terms, or background info) to guide the recognition process »), 17/10/2026"},{"appuie":["langues"],"lu":"https://huggingface.co/microsoft/VibeVoice-ASR-HF/raw/main/README.md (« It supports over 50 languages, requires no explicit language setting, and natively handles code-switching within and across utterances. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://huggingface.co/microsoft/VibeVoice-ASR-HF/raw/main/README.md (« ## VibeVoice-ASR (Transformers-compatible version) »), 17/10/2026"},{"appuie":["sortie"],"lu":"https://raw.githubusercontent.com/microsoft/VibeVoice/main/README.md (« 2026-03-06: 🚀 VibeVoice ASR is now part of a »), 17/10/2026"},{"appuie":["langues"],"lu":"https://huggingface.co/microsoft/VibeVoice-ASR-HF/raw/main/README.md (« - ko - fr - ru »), 17/10/2026"},{"appuie":["langues"],"lu":"https://raw.githubusercontent.com/microsoft/VibeVoice/main/docs/vibevoice-asr.md (« | MLC-Challenge | French | »), 17/10/2026"}],"classements":[{"id":"transcription/francais","nom":"Transcription en français","rang":38,"sur":39,"valeur":14.04,"unite":"%","chiffres":{"rtfx":125.68,"jeux":{"Common Voice":23.85,"FLEURS":11.3,"MLS":6.96}},"voisins":["openmoss-team-moss-transcribe-diarize","meta-omniasr-ctc-300m-v2"],"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"}},{"id":"transcription/open-asr-anglais","nom":"Transcription en anglais, Open ASR","rang":44,"sur":53,"valeur":8.16,"unite":"%","chiffres":{"rtfx":216.36,"jeux":{"AMI-Cleaned":12.02,"Earnings22-Cleaned-AA-chunked":7.97,"Gigaspeech-Cleaned":7.87,"LS Clean":1.56,"LS Other":4.95,"Private (conversational)":14.62,"Private (scripted)":11.09,"SPGISpeech":3.47,"URGENT24":19.5,"Voice Arena Monsoon":4.74,"Voxpopuli-AA-Cleaned":2.02}},"voisins":["meta-omniasr-llm-7b-v2","edge0-audio8-asr-0-1b"],"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":"microsoft/VibeVoice-ASR-HF"}}