C-LARA

This week, I have been working on “reading histories”, additions to simple C-LARA, cleaning up the layout, and better support for Japanese:

‘Reading histories’

Reading histories now support phonetic texts. They seem to work as intended, but I haven’t yet tested them thoroughly enough.

Note that you can only include a text in a reading history if it’s both been posted to the social network, and if it’s been rendered recently enough that it has the stored information the reading history mechanism requires. So if you find you can’t include a text, re-render it and make sure it’s been added to the social network.

Additions to simple C-LARA

You can now create a simple C-LARA text from an image as well as from a text prompt. I posted about that here.

Cleaning up the layout

I have started cleaning up the layout: the first step has been to replace the ugly list of links at the top of the page with a proper navigation bar. I’ve also fixed some issues that Pauline pointed out. I’ve posted about that here and here.

There are still plenty of things left to clean up. Chadi pointed out a couple of problems with right-to-left languages, that’s next on my list.

Better handling of Japanese

It turned out that performance in Japanese was absolutely terrible. Adding some sensible prompt templates and examples has made it a lot better, though it would be good to get detailed comments from people who are familiar with the language.

Next Zoom call

Thu Feb 15, 2023, 20:00 Adelaide (= 09.30 Iceland = 09.30 Ireland/Faroe Islands = 10.30 Europe = 11.30 Israel = 13.00 Iran = 17.30 China = 20:30 Melbourne/New Caledonia)