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
Not publishing Transformers option until PR is official?
#22
by ACloudCenter - opened
I've been struggling for the last hour trying to get my space to use the VV1.5 from the transformers library. I noticed that it existed under "use this model" as of yesterday. However, after trying to push to my space and getting errors about not being found, I realized that there is still an open PR https://github.com/huggingface/transformers/pull/40546/files . I know this is probably an edge case and usually a non-issue, but maybe not exposing the transformer option in the model space will avoid confusion in cases like this.
