Not in the library itself, it’s pure inference. Some models have this trained out of them anyhow. Otherwise this is a post processing task which is not really inference

▲

dostick 10 hours ago | parent [-]

So it looks like something that app would be doing, or run another model over the output to smoothen out and remove these things?

	▲	sipjca 9 hours ago \| parent [-]
		Yep, could do simple things like literal regex or all the way up to LLM cleanup, tons of options