Closed erikvullings closed 2 years ago
Sorry for the late answer, some summer vacation in the way 😄
After investigation, it looks like this specific sentence is confused by the family name, which contains unusual sequence of letters for english Matytsin
repeated 8 times.
In a more recent build I slightly increase the number of chunk analyzed for long texts, which reduce the risk of this happening.
For this quote, I get the following result with version 1.3.0
[
{ lang: 'en', accuracy: 0.6393910561370124 },
{ lang: 'lt', accuracy: 0.36060894386298764 }
]
I like your library/tool as it is simple to use, compact, and generally produces good results, but I do have an issue/question. Why does it classify the following block as
lt
?