model_config.py

from transformers import PretrainedConfig
from typing import Tuple


class AudioMAEConfig(PretrainedConfig):
    model_type = "audiomae"

    def __init__(self,
                 img_size:Tuple[int,int]=(1024,128),
                 in_chans:int=1,
                 num_classes:int=0,
                 **kwargs,):
        super().__init__(**kwargs)
        self.img_size = img_size
        self.in_chans = in_chans
        self.num_classes = num_classes