Instructions to use facebook/mms-1b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/mms-1b with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForPreTraining processor = AutoProcessor.from_pretrained("facebook/mms-1b") model = AutoModelForPreTraining.from_pretrained("facebook/mms-1b") - Notebooks
- Google Colab
- Kaggle
How to convert fairseq mms to hf format
#2
by Yunus - opened
Can you explain how you converted the fairseq model weights into hf format
See conversion script here: https://github.com/huggingface/transformers/pull/23813