Automatic Speech Recognition
Transformers
Safetensors
phi4mm
text-generation
nlp
code
audio
speech-summarization
speech-translation
visual-question-answering
phi-4-multimodal
phi
phi-4-mini
custom_code
Eval Results
Instructions to use microsoft/Phi-4-multimodal-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/Phi-4-multimodal-instruct with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="microsoft/Phi-4-multimodal-instruct", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("microsoft/Phi-4-multimodal-instruct", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
HF format chat template
#56
by RaushanTurganbay HF Staff - opened
No description provided.
RaushanTurganbay changed pull request status to open
nguyenbh changed pull request status to merged
We have to revert this merge since Phi4MMProcessor does not support chat template.
Sorry wasn't meant to be merged yet! It is part of conversion to transformers shipped Phi-4. The chat template is supported internally in transformers and makes it easier to run generation in few lines few code. The PR that needs to be merged first is #55, but I am thinking now that we could make a new model like microsoft/Phi-4-multimodal-instruct-hf to not break it for current users