How to use shivam/wav2vec2-xls-r-300m-hindi with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="shivam/wav2vec2-xls-r-300m-hindi")
# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("shivam/wav2vec2-xls-r-300m-hindi") model = AutoModelForCTC.from_pretrained("shivam/wav2vec2-xls-r-300m-hindi", device_map="auto")
