microsoft/Phi-4-multimodal-instruct
microsoftautomatic-speech-recognitionmit
Developed by microsoft in 2025, microsoft/Phi-4-multimodal-instruct is a automatic-speech-recognition model. With 509.3K downloads and 1.6K likes, it is widely used. It is distributed under the mit license.
About microsoft/Phi-4-multimodal-instruct
microsoft/Phi-4-multimodal-instruct — a automatic-speech-recognition model on the Hugging Face Hub.
LLM pricing & performance
Full LLM page →microsoft/Phi-4-multimodal-instruct is available via API — live cost, context, and benchmark data:
Input / 1M
$0.00
Output / 1M
$0.00
Context
128K
Tokens/sec
—
Details
- Provider
- microsoft
- Task
- automatic-speech-recognition
- Library
- transformers
- License
- mit
- Released
- 2025-02-24
- Downloads
- 509323
- Likes
- 1606