search

interscript / rababa

Rababa, the diacritization library for Arabic and Hebrew (Abjad scripts in general)
12 stars 1 forks source link

Test Rababa on GNDB Arabic data #5

Open ronaldtse opened 3 years ago

ronaldtse commented 3 years ago

This is easier than #4 :

  1. Fetch ara_Arab2Latn_BGN_1956.csv (27.9MB) from https://github.com/interscript/geonames-transliteration-data/releases/download/v20210705/pairs.zip

  2. Run the NNets on Arabic (SRC_FULL_NAME_RO column)

image

  1. Run the output of step 2 using Interscript system (ara_Arab2Latn_BGN_1956 is this one: https://www.interscript.org/systems/bgnpcgn-ara-Arab-Latn-1956)

  2. Compare the output of ara_Arab2Latn_BGN_1956.csv column DEST_FULL_NAME_RO and output of step 2.

ronaldtse commented 3 years ago

@gilgameshjw is doing this.