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
Taking infinite time on a specific audio transcription (less than 40s)
#61
by FloTeur - opened
Hello,
I'm currently transcribing audio and using VAD to segment my audio into smaller ~30-second parts. This method worked well for five audio files, but the last one is taking an unusually long time to transcribe. Has anyone else encountered this issue?
I restarted my kernel rebooted my computer but it still bug. It is a quite difficult audio very noisy and not loud at all.
Okay, I corrected it by canceling noise and normalizing the audio. Sorry for the post.
nguyenbh changed discussion status to closed