[dostick]

Does this support filtering of “umm”,”err”, “ugh”, or that is nit yet possible with open source models?

[sipjca]

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]

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]

Yep, could do simple things like literal regex or all the way up to LLM cleanup, tons of options