Nice! Can I try the Spanish one?
If you speak any of the languages in this page https://lang.relays.land/ and you've been looking all your life for a reasonably safe relay that only accepts notes in your language then you're invited to try it now.
Let me know so I can add you and then you can invite others.
Discussion
I've added you and nostr:npub1kcnfmfzfj20yj4d7p8hgh53hlrmfta4aqj2ftmmz6t5vxen6g34qnqacup and nostr:npub107jk7htfv243u0x5ynn43scq9wrxtaasmrwwa8lfu2ydwag6cx2quqncxg. Portuguese has about 130 members now, please invite more people and beat that number.
Impossible, I'm a bot.
Awesome, thanks! Let’s find some Spanish speaking friends
😢
qué raro, yo he podido publicar. voy a reenviar una nota tuya al relay para que puedas escribir sin problema.
Gracias nostr:npub107jk7htfv243u0x5ynn43scq9wrxtaasmrwwa8lfu2ydwag6cx2quqncxg! Acabo de intentar nuevamente y tampoco funciona, pero me he dado cuenta que no tengo notas en español para reenviar, quizás con esta funcione(?) buen viernes de todas formas!
i got rate limited lol but added a bunch of people already
what are you using to detect languages? getting lots of false negatives
This thing: https://github.com/pemistahl/lingua-go
And requiring a confidence score of at least 0.9. It was good in my tests but I've only tested Portuguese.
I'll decrease it to 0.85.
And relax the ratelimit a little bit.
sounds good, thanks! looks like anglicisms and internet slang reduce the confidence score.
I'm using this library on adre.su too, but I have to say, the Confident Score didn't help me at all. I tried their "light mode", implemented rate limits, and in the end, I gave up on checking short messages. But honestly, it all doesn't work very well. The best results came from manual calibration with similar languages specified (for each one used), but this whole language thing takes a lot of resources, and manual setup even more so.
I don't know, after removing URLs and URIs and trying a bunch of examples with Spanish, Portuguese and Chinese I'm yet to find a single false positive or negative.
But also I'm only testing if some text matches one specific language, not trying to "detect", so maybe that helps.