How to use ybelkada/tiny-wav2vec2-stable-ln with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="ybelkada/tiny-wav2vec2-stable-ln")
# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("ybelkada/tiny-wav2vec2-stable-ln") model = AutoModelForCTC.from_pretrained("ybelkada/tiny-wav2vec2-stable-ln")
SFconvertbot