[
https://issues.apache.org/jira/browse/TIKA-2790?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16707521#comment-16707521
]
Ken Krugler commented on TIKA-2790:
-----------------------------------
Yalder is about 2-2.5x faster than language-detector, depending on the size of
the models (and thus the accuracy) that you want. I'm thinking I should train
and test on the Leipzig corpus - I wonder if OpenNLP has published any
performance figures?
> Consider switching lang-detection in tika-eval to open-nlp
> ----------------------------------------------------------
>
> Key: TIKA-2790
> URL: https://issues.apache.org/jira/browse/TIKA-2790
> Project: Tika
> Issue Type: Improvement
> Reporter: Tim Allison
> Priority: Minor
>
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
