Sebastian Öjefors

Ah.. Damn it Windows. It's a strange issue, because you would think that setting the input & output of the CLI would be all there is to it. And it...

As long as the CLI you use is set to UTF-8, translation is now correct & encoding works as it should on the fixed Qt5 build. Using translateLocally with the...

> When you say doesn't work, do you mean that the old behaviour is preserved in this case? Not exactly.. `echo Hello, how are you? | .\\translateLocally -m en-es-tiny -o...

> Yes. Generally, _we_ train the models with data where we don't change the quotation marks. So if the French translation of a sentence uses `«»` but the English uses...

> We try to not do to much language-specific editing of the translation output (often called post-editing) because then we need to implement that in the translator for each language...

> Vocabulary is gathered from _clean_ training data that we believe offers an accurate word distribution of the languages we translate. Cool! > 1. Users hate to see all upper/lowercase...

That's great to hear! I hope you'll get more support in the future, it's duly deserved.

Okay, thank you! Quality scores would have been neat but I'm mostly interested in alignment tokens. However, I assume that they can not be returned through Native Message either then....

> So I'm not entirely sure how much work translateLocally can do here for you, or how much we should just dump that info in the native message response and...

> How big are your translation requests generally? Are they just one or a couple of sentences, or more? It would be very dependent on the user case & the...