microsoft/Phi-4-multimodal-instruct

huggingface.co
On the map Visit site

Модель automatic-speech-recognition · лицензия mit

Installation

from transformers import pipeline; pipeline(model="microsoft/Phi-4-multimodal-instruct")
Installs intotransformers, python
Not sure where to start — ask an assistant to walk you through:

Specs

Type Model
SectionModels & platforms / automatic-speech-recognition
Pricing open source
Platform Web only
Hostingcloud
Installpackage
Installs intotransformers, python
Site languageen
Vendormicrosoft
Views292 512
Launched2025-02-24

Can do

automatic-speech-recognition

Tags

transformers safetensors en text-generation zh custom_code de fr ar multilingual automatic-speech-recognition code audio nl cs da fi nlp phi visual-question-answering speech-translation phi4mm phi-4-mini phi-4-multimodal speech-summarization

Found in sources

huggingface

Similar in «Models & platforms»

DeepSeek V3
Cost-efficient open-source MoE model rivaling GPT-4o in reasoning and math tasks
DeepSeek
Open reasoning and coding models on par with the top closed ones.
Mistral AI
European open and commercial models, Le Chat and Codestral.
sider.ai
Research faster with Sider AI—summarize web pages, take notes, generate reports, and chat with leading AI models. Powered by ChatGPT, Gemini, Claude, Grok, Deepseek, etc. Try the best AI sidebar now!
Hugging Face
The hub of models and datasets: millions of weights, Spaces, Transformers.
doubao.com
Передовая мультимодальная AI-платформа от ByteDance с современными языковыми, визуальными и речевыми моделями, а также интегрированными возможностями рассуждения и поиска.

Submit a site to the catalog

Just send the link — we will work out the rest.

We will review what you send and add it to the catalog if it fits.