Rendered at 12:31:53 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
vunderba 9 hours ago [-]
Nice job.
A lot of early “fantasy word” generators worked in a similar way - by using n-grams at a character (or character chunk) level rather than the word level even if the breaks didn’t align with syllables.
I don't know if it was ever done - but adapting a Markov model built out against a corpus of word IPAs treating each phoneme as a symbol in the chain would have produced better results as well.
sim04ful 15 hours ago [-]
I love this. It's so difficult to coin words that both sound familiar but are unique.
alexakten 15 hours ago [-]
It almost like a slot machine, the perfect word combo might come on the next spin haha! I'm glad you like it.
KomoD 15 hours ago [-]
I would like it more if it didn't blur during generation. I can see through the blur that it has already made the word, so I don't really get the point of hiding it from me.
alexakten 15 hours ago [-]
Should feel faster now. When it has fetched both words it reveals them instantly, the blur only happens on the fade out animation while the fetch is happening. Thanks for the feedback!
sim04ful 15 hours ago [-]
Some of my favorites:
Disquake
obvermeiled
obinn
i'm curious how did you make the two word-gen merge so naturally ?
A lot of early “fantasy word” generators worked in a similar way - by using n-grams at a character (or character chunk) level rather than the word level even if the breaks didn’t align with syllables.
I don't know if it was ever done - but adapting a Markov model built out against a corpus of word IPAs treating each phoneme as a symbol in the chain would have produced better results as well.
i'm curious how did you make the two word-gen merge so naturally ?