Model Card
Overview
- Model name: Arabic2English Translation
- Model description: Translates between Arabic and English.
- Authors: Alif Al Hasan
- Repository link: https://huggingface.co/spaces/alifalhasan/arabic2english/tree/main
- License: MIT
- Contact information: [email protected]
Arabic2English Translation
A simple and well designed web app to translate between Arabic and English.
Requirements
- gradio
- torch>=1.6
- torchtext==0.6
- transformers
- nltk
- pandas
- spacy
- https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.7.1/en_core_web_sm-3.7.1-py3-none-any.whl
Table Of Contents
Introduction
A simple and well designed web app to translate between Arabic and English.
Prject Architecture
βββ data
β βββ arabic2english.txt - text dataset.
β
β
βββ docs
β βββ arabic2english.pdf - paper of the related research.
β
β
βββ models
β βββ arabic2english.pt - generated model.
β
β
βββ src
β βββ data_processing
β βββ data_processing.py - this module preprocesses the input data.
β βββ train
β βββ train.py - this module trains and saves the model.
β βββ transformer.py - model file.
β βββ translation
β βββ translate.py - this module translates the input sentence.
β
β
βββ app.py - this module starts the app interface.
β
β
βββ LICENSE - license file of this project.
β
β
βββ README.md - readme file of this project.
β
β
βββ requirements.txt - list of required packages.
How To Run
# clone project
git clone https://huggingface.co/spaces/alifalhasan/arabic2english
# go inside the project directory
cd arabic2english
# install the required packages
pip install -r requirements.txt
# train & save the model
python src/train/trainer.py
# run the gradio app
python app.py
License
Distributed under the MIT License. See LICENSE
for more information.
Contributor
Alif Al Hasan - @alifalhasan - [email protected]
Project Link: https://huggingface.co/spaces/alifalhasan/arabic2english
- Downloads last month
- 18
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.