I have found a finet-tuned model for my language in huggingface and want to use it with transformers to transcribe and audio !
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
processor = AutoProcessor.from_pretrained("arbml/whisper-largev2-ar")
model = AutoModelForSpeechSeq2Seq.from_pretrained("arbml/whisper-largev2-ar")
How to apply this code on the audio file ! How to upload the audio with librosa or what format and to do transcribe from arabic into arabic where to apply tokenization?