Instructions to use facebook/mms-300m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/mms-300m with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForPreTraining processor = AutoProcessor.from_pretrained("facebook/mms-300m") model = AutoModelForPreTraining.from_pretrained("facebook/mms-300m") - Notebooks
- Google Colab
- Kaggle
model._get_adapters() for 300m model not available
#3
by Jungwonchang - opened
I tried to fine-tune 300m model on my custom dataset, but was unable to do so.
The error message was shown as below
ValueError: <class 'transformers.models.wav2vec2.modeling_wav2vec2.Wav2Vec2ForCTC'> has no adapter layers. Make sure to define `config.adapter_attn_dim`.
I tried, but the results were horrible compared to 1b models