while fine_tuning is True during training quantizer, what has to be base_mel_path as input?

MQTTS/quantizer/meldataset.py

Line 153 in be5c48f

os.path.join(self.base_mels_path, os.path.splitext(os.path.split(filename)[-1])[0] + '.npy'))

by default, it's none in train.py

also, the do_0000xxx checkpoint saved during training the quantizer, I would like to know where it is used, if used in training the 100M VQTTS