How to use milanakdj/whisper-small-full-tibetan with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="milanakdj/whisper-small-full-tibetan")
# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("milanakdj/whisper-small-full-tibetan") model = AutoModelForSpeechSeq2Seq.from_pretrained("milanakdj/whisper-small-full-tibetan", device_map="auto")
