Instructions to use facebook/musicgen-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/musicgen-small with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-audio", model="facebook/musicgen-small")# Load model directly from transformers import AutoProcessor, AutoModelForTextToWaveform processor = AutoProcessor.from_pretrained("facebook/musicgen-small") model = AutoModelForTextToWaveform.from_pretrained("facebook/musicgen-small") - Notebooks
- Google Colab
- Kaggle
How to export musicgen-small to ONNX model for deploy on special devices
#19
by Qingjie920 - opened
i want to deploy musicgen-small model to special devices which support ONNX model, then i have to convert musicgen-small model to ONNX, i split the musicgen model to LM and compression, now compression was converted to ONNX properly, but LM model failed. do you have any suggestions?
Hi team?
May i get any update on this query? it will be useful to deploy model any edge devices if we get ONNX model.
May i know if we have plan/schedule to support onnx model for musicgen-small?
Hi @Qingjie920 @BoscoTheDog here is the related open issue: https://github.com/huggingface/optimum/issues/1297
A PR is open here for the ONNX export support: https://github.com/huggingface/optimum/pull/1779
@xenova is actively working to make Musicgen work with transformers.js.