sepinf-inc / IPED

IPED Digital Forensic Tool. It is an open source software that can be used to process and analyze digital evidence, often seized at crime scenes by law enforcement or in a corporate investigation by private examiners.
Other
943 stars 218 forks source link

New Text Translation task module #1180

Open lfcnassif opened 2 years ago

lfcnassif commented 2 years ago

Inspired also by this: http://sleuthkit.org/autopsy/docs/user-docs/4.19.3/machine_translation_page.html

Of course, differently from them, I think we should do it while processing and submit the translated text to all other text processing modules: regex, ner, indexing...

lfcnassif commented 2 years ago

Quoting @mobab-th:

for offline Translation LibreTranslate (https://libretranslate.com/) could be used. In my tests the results are useful but the performance is not so good.

lfcnassif commented 2 years ago

Its license is AGPL, it may be integrated as a plugin module (before we makes TSK a plugin to fully comply with GPL #523)

lfcnassif commented 1 year ago

A few more possible libraries to use brought to my knowledge today: https://github.com/argosopentech/argos-translate https://github.com/facebookresearch/seamless_communication

Any others?