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