fleanend / NMT_ofi

This project implements a simple transliterator to convert words from the Ligurian language (written in the Grafîa Ofiçiâ) to their pronunciation (written with IPA symbols). Under the hood the transliterator uses a character level Encoder-Decoder architecture with Attention.'

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Neural Machine Transliteration

Grafîa Ofiçiâ (Ligurian Language) to IPA

This project implements a simple transliterator to convert words from the Ligurian language (written in the Grafîa Ofiçiâ) to their pronunciation (written with IPA symbols).

Under the hood the transliterator uses a character level Encoder-Decoder architecture with Attention.

Install

Download the pretrained model from here, unzip the contents in ./models

Create a virtual environment in yout preferred way and activate it.

Install requirements:

pip install -r requirements.txt

Sample Usage

From the repo root run:

python bin/transliterate.py

Data

You can check the data I used for training this model here.

Acknowledgements

Thanks to Bishal Santra, whose code and models I used as a basis for mine.

About

This project implements a simple transliterator to convert words from the Ligurian language (written in the Grafîa Ofiçiâ) to their pronunciation (written with IPA symbols). Under the hood the transliterator uses a character level Encoder-Decoder architecture with Attention.'

License:MIT License


Languages

Language:Python 100.0%