I think was deployed. Marking as resolved. Let me know if this isn't true.

@Halfak knows far more than me about the implications of using old datasets for training, but +1 to building a model and see how well it works before we spend the time gathering additional data.

Thanks all for getting this deployment out!

+1 an exception. Sorry all for the blockage.

Agreed, this is really great. Let's test it out with some different types of data (audio, text, images, etc) and have some community members test it out. If it works well (both in data loading, data labeling and data export) then lets create some tutorials for ourselves and the community on mw:machinelearning

I just want echo elukey's comments. The community is front and center to our mission as a team. And doing that means keeping high maintainability and stability in the system. I don't think we've ran into any major issues yet but it is future proofing against any issues in the future. What I don't want is volunteers to feel that we don't appreciate their work.

I like the idea, but instead of the evaluation criteria being small wikis, we should look at popular vs. unpopular wikis in terms of API requests.

Awesome, thanks Peachy88

Thank you @Theofpa!

Would it be possible to get all ORES scores ever as a one-off-job and then dump them online somewhere?

Just seconding Chtnnh here. More technical details in approach would help the evaluation process.

Thanks Chtnnh for helping Vini7148!

Oh awesome thanks Isaac. Where do you host the Python code?

This looks super interesting, when the data is out there I'd love to have it posted for a potential internship or GSoC project.

Sounds great! Can you post here when the model is up on toolforge? I'd love to take a look.

This is a good lesson for us about adding custom model library services into Lift Wing. That said, I suspec fastText is the easy case because it is so well supported generally.

Let's try whichever one is the easiest to start out with. That'll give us a good idea of the lowest hanging fruit are.

None yet, but soon

Just to second what @fdans said, the data detective work was great and this was such a fun ticket to watch.

@kevinbazira did a great pass, I need to do another to update a lot of the language.

oh right, I remember really struggling with enchant. Yeah, I might work on a docker image to do this because it was really brutal last time to config my environment

Great, it all looks good. I am going to close this task

kbazira needs access too

I approve