Skip to main content
Version: Next

ETNLTK Intro

Let's discover Ethiopian Natural Language Toolkit (etnltk) ๐Ÿ˜Š.

Objective:

  • The Ethiopian Natural Language Toolkit (ETNLTK) project aimed to develop a suite of open source Natural Language Processing modules for the Ethiopian languages.

Why?

  • Most of resourced languages such as English and other European countries has tools such as NLTK, SPACY, CLTK and many more that allows to perform text preprocessing, but the same history is not true for Ethiopian local languages.

Inspirations:

  • The Ethiopian Natural Language Toolkit (etnltk) is built using python language and takes inspiration from spacy and nltk libraries.

Getting Startedโ€‹

Get started by Installation.

pipโ€‹

PyPI version

  • Python version 3.6 or above:

    • We recommend that you install etnltk via pip, the Python package manager. To install, simply run.
    pip install etnltk

From Sourceโ€‹

  • Alternatively, you can also install from source via etnltk git repository, which will give you more flexibility in developing on top of etnltk. For this option, run:

    git clone https://github.com/robikieq/etnltk.git

    cd etnltk

    pip install -e .

Amharic: แŠ แˆ›แˆญแŠ›โ€‹

Take a look at Usage Amharic for more.

  • The language serves as the official working language of the Ethiopian federal government.
  • Spoken by more than 100M people arroung the world and all over Ethiopia.
  • Amharic is written left-to-right using a system that grew out of the Geสฝez script.
  • The writing system is called fidรคl (แŠแ‹ฐแˆ) in Ethiopian Semitic languages.