Instructions to use facebook/encodec_24khz with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/encodec_24khz with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="facebook/encodec_24khz")# Load model directly from transformers import AutoFeatureExtractor, AutoModel extractor = AutoFeatureExtractor.from_pretrained("facebook/encodec_24khz") model = AutoModel.from_pretrained("facebook/encodec_24khz") - Notebooks
- Google Colab
- Kaggle
`AutoProcessor` cannot load the processor properly
#2
by alifarokh - opened
Hi everyone.
The sample code in the model card cannot load the processor properly. Here is the code and the result:
from transformers import AutoProcessor
processor = AutoProcessor.from_pretrained("facebook/encodec_24khz")
Result:
Could not find image processor class in the image processor config or the model config. Loading based on pattern matching with the model's feature extractor configuration.
The code is tested both on my local server and on Google Colab. Also, I have tried different versions of transformers (4.31.0, 4.32.0, etc.)
Please let me know how I can fix the problem.
Thank you in advance.