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)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("microsoft/Phi-4-multimodal-instruct", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Fix image embedding logic to be mps-compatible
Verified signatureAddresses the assertion error raised on mps machines. Cf. https://huggingface.co/microsoft/Phi-4-multimodal-instruct/discussions/12 - MPS changes: - `.bool()` instead of `.type(torch.BoolTensor)` - Avoid `index_put` issues by having an mps-specific logical block. - The `temp_len` variable in the assertion was never used anyway, so I removed the variable and the offending assertion. - Various clean up of comments and code.f580f2d
-
fixes the asserion error when num_beams > 1 (#42)
Verified signature- fixes the asserion error when num_beams > 1 (2258faa22fbe042d3c73b0545fb9f1feaf59ab51) Co-authored-by: Yiming Wang <freewym@users.noreply.huggingface.co>18812f4 -
Update readme
Verified signature3fb546e -
Add Appendix B: Fine-tuning Korean speech (#40)
Verified signature- Add Appendix B: Fine-tuning Korean speech (54560a99ae1ef6b9d209b9e25441d621deaccfc0) Co-authored-by: Daekeun Kim <daekeun-ml@users.noreply.huggingface.co>73148fe
-
Update readme
Verified signature985802b -
Fix bug with safe suffix removal (#34)
Verified signature- Safe suffix removal (507cf490804a20826b1defcf7f4dbf9af57a0f78) Co-authored-by: Junkun Chen <shtpgshus@users.noreply.huggingface.co>eac2ca5
-
update readme
Verified signature607bf62 -
update readme
Verified signaturea34dad0 -
Update Readme
Verified signature4927696 -
Update readme
Verified signature1ea5d67
-
Update readme
Verified signaturea11e830
-
Update playgrounds
Verified signature3912553 -
Add language tags (#8)
Verified signature- Add language tags (4f01ad5164221e4037afeb77d1c5e2402075f3fb) Co-authored-by: Loïck BOURDOIS <lbourdois@users.noreply.huggingface.co>879783f -
Update README.md (#2)
Verified signature- Update README.md (faf353bc39506c48383e5b28e743c37a601fc33b) Co-authored-by: aergsfxds <fasdfgaer@users.noreply.huggingface.co>1622ae1
-
Update readme
Verified signature4f70fd2 -
Update README.md
Verified signatureafbb57c
-
Update Readme
Verified signaturebbef147 -
Update Readme
Verified signature1be8bb6 -
update blog url
Verified signature5edcd2b -
update readme
Verified signature6fa2bd8 -
Update the video
Verified signaturee47648d -
update readme
Verified signature95e4ccf -
added technical report
7fe753a
-
Update examples
nguyenbh17df1f5 -
Add examples
nguyenbhbd4b39b
-
Added model files
d93d2f6 -
initial commit
Verified signature1023f0d