Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Exactly. If you type "I am a dangerous asdhfjahdsff velociraptor, rawr."

There aren't entries for

- asdhfjahdsff

- rawr

I added around 500 new words, but I missed a lot of stuff.

The ultimate fix is to have grapheme -> phoneme prediction so that all unseen words can be mapped to potential phonemes (polyphones).



Are you logging the words people submit? That'd be a good source for the most common OOV tokens to add.


I tried "Watch as the cat sniffs the flower, eats it, and then vomits. This is classic feline behavior" with Attenborough. He seems to slip into a bit of a German accent on the second sentence. What's the cause of that?

Thanks for sharing, though. Very interesting project!




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: