Keep differentiable LSTM on cuDNN eecd3e6
Project Beatrice commited on
How to use prj-beatrice/utmos22-torch-native with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("audio-classification", model="prj-beatrice/utmos22-torch-native", trust_remote_code=True) # Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("prj-beatrice/utmos22-torch-native", trust_remote_code=True, device_map="auto")