> For the complete documentation index, see [llms.txt](https://textav.gitbook.io/textav-event/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://textav.gitbook.io/textav-event/projects/palestinian-remix.md).

# Palestinian Remix

{% embed url="<https://www.youtube.com/embed/CzAP_au2ltM>" %}

## Notes:

* Project : <http://PalestineRemix.com> 20 documentaries in 4 languages (English, Arabic, Hebrew, Bosnian) - Based on Hyperaud.io technology.
* When people say that they have transcripts they may not have them in the format that you need.
* Getting transcripts in a word document… in tables…??? Built a tool with a vertical timeline, each paragraph with tabs for each language.
* Helped by QCRI who use Kaldi and have a very good arabic language model.
* To deal with hardcoded subtitles: Duplicate video and in javascript canvas, frame-by-frame matching looking for changes in the subtitles, and send it to tesseract server-side with English back (with bad spelling because hard to do).
* “One night I managed to write something terrifying like this …”