upper bound and larger bound inconsistent with step sign

[ghosthunterk]

Hi, I'm trying to batch predict on some speech CSVs, at first some audio segments are a bit lengthy which caused the problem of #11, so I saved the new model as with new max as 5500: nisqa_tts_5500 and nisqa_all_5500, the models seem to predict fine until the problem of "upper bound and larger bound inconsistent with step sign" show up.