How to use marcel/wav2vec2-large-xlsr-53-german with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="marcel/wav2vec2-large-xlsr-53-german")
# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("marcel/wav2vec2-large-xlsr-53-german") model = AutoModelForCTC.from_pretrained("marcel/wav2vec2-large-xlsr-53-german", device_map="auto")
How to fix it?
