{"id":"microsoft-phi-4-multimodal-instruct","nom":"Phi-4-multimodal-instruct","editeur":"Microsoft","pays":"États-Unis","poids_ouverts":true,"poids_selon":null,"licence":"MIT","licence_selon":null,"liens":{"page":"https://huggingface.co/microsoft/Phi-4-multimodal-instruct"},"fiche_auto":true,"page":"https://quelleia.com/voix/modeles/microsoft-phi-4-multimodal-instruct/","releve":"2026-10-19","en_bref":"17e sur 39 en transcription en français.","presentation":"Petit modèle multimodal ouvert de la famille Phi, qui prend en entrée texte, image et audio et répond en texte. Côté voix, il assure transcription et traduction de la parole dans un seul modèle, sans chaîne de deux modèles.","sortie":"2025-02","taille":"5,6 milliards de paramètres","langues":{"annoncees":{"annoncees":"8 langues pour l'audio, dont le français","nombre":8,"francais":true,"liste":["en","zh","de","fr","it","ja","es","pt"]},"prises_en_charge_selon_open_tts":null,"evaluees":["fr"]},"preuves":[{"appuie":["presentation"],"lu":"https://huggingface.co/microsoft/Phi-4-multimodal-instruct/raw/main/README.md (« The model processes text, image, and audio inputs, generating text outputs, and comes with 128K token context length. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://huggingface.co/microsoft/Phi-4-multimodal-instruct/raw/main/README.md (« To achieve this, users needed to use a pipeline of two models: one model to transcribe the audio to text, and another model for the language or vision tasks. »), 17/10/2026"},{"appuie":["langues"],"lu":"https://huggingface.co/microsoft/Phi-4-multimodal-instruct/raw/main/README.md (« + Audio: English, Chinese, German, French, Italian, Japanese, Spanish, Portuguese »), 17/10/2026"},{"appuie":["taille"],"lu":"https://huggingface.co/microsoft/Phi-4-multimodal-instruct/raw/main/README.md (« Phi-4-multimodal-instruct has 5.6B parameters and is a multimodal transformer model. »), 17/10/2026"},{"appuie":["sortie"],"lu":"https://huggingface.co/microsoft/Phi-4-multimodal-instruct/raw/main/README.md (« Release date:** February 2025 »), 17/10/2026"}],"classements":[{"id":"transcription/francais","nom":"Transcription en français","rang":17,"sur":39,"valeur":5.04,"unite":"%","chiffres":{"rtfx":127.69,"jeux":{"Common Voice":6.89,"FLEURS":4.08,"MLS":4.14}},"voisins":["speechmatics-enhanced","meta-omniasr-llm-7b-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"}}],"noms_dans_les_sources":{"hf_audio":"microsoft/Phi-4-multimodal-instruct"}}