Instructions to use microsoft/VibeVoice-1.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/VibeVoice-1.5B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="microsoft/VibeVoice-1.5B")# Load model directly from transformers import AutoModelForSeq2SeqLM model = AutoModelForSeq2SeqLM.from_pretrained("microsoft/VibeVoice-1.5B", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Running in ComfyUI on MAC M3 Ultra with 512GB of memory.
#34
by garryo - opened
Anyone else running the 1.5B on MAC? I tried running the multi voice with 2 voices and a 20 minute podcast script from one of my "The AI Morning Read" podcast episode and it actually ran out of memory and locked up the MAC! never seen anything do that before. I was watching performance because it was running long and when it hit 508GB of memory usage it started reporting force quit apps to free memory then it tripped over 512GB and locked.
How are you able to get past 2 minutes?