search

FelipeLuz / dotnet-bad-word-detector

.NET library that uses machine learning to detect bad words (profanity) within a string.
Apache License 2.0
14 stars 1 forks source link

Support for Additional Languages #2

Open pval99 opened 7 months ago

pval99 commented 7 months ago

Hey there!

I've been using your dotnet-bad-word-detector, and it's awesome! I was wondering about adding more languages to it, especially the top five spoken ones worldwide. That would make it super useful. Is there a plan for this, or could you guide me on how I might help to make it happen? If there's a way to contribute or if you've got any tips on training it with new languages, I'm all ears.

Thanks!

FelipeLuz commented 7 months ago

Hey @pval99, it's nice that you are using it and you liked the lib, I kind of just forgot it existed for a while and came back today to upgrade it to .Net 8.

To add a new language would be helpful just a CSV list of curse words, and then I can easily train a new model for that language. If you can provide that I release a new version with this upgrade.

pval99 commented 7 months ago

Thanks for the help, I would be nice to add the language source words to the repo for public use. I will make English, Spanish, Portuguese and Russian profanity words lists and then make a pull request for you to train the model.

veudal commented 1 month ago

Any updates on multi language support?