metadata
language: african-languages
tags:
- african-languages
- machine-translation
- text
license: apache-2.0
model-index:
- name: Masakhane Benchmark Models
results:
- task:
name: Machine Translation
type: machine-translation
dataset:
name: masakhane benchmarks
args: african-languages
Interacting with the Masakhane Benchmark Models
I created this demo for very easy interaction with the benchmark models on Masakhane which were trained with JoeyNMT(my forked version).
To access the space click here.
To include your language, all you need to do is:
- Create a folder in the format src-tgt/main for your language pair, if it does not exist.
- Inside the main folder put the following files:
- model checkpoint. Rename it to
best.ckpt
. config.yaml
file. This is the JoeyNMT config file which loads the model an pre-processing parameters.src_vocab.txt
file.trg_vocab.txt
file.
- model checkpoint. Rename it to
The space currently supports these languages:
source language | target language |
---|---|
English | Swahili |
English | Afrikaans |
English | Arabic |
English | Urhobo |
English | Ẹ̀dó |
Efik | English |
English | Hausa |
English | Igbo |
English | Fon |
English | Twi |
English | Dendi |
English | Ẹ̀sán |
English | Isoko |
English | Kamba |
English | Luo |
English | Southern Ndebele |
English | Tshivenda |
Shona | English |
Swahili | English |
Yoruba | English |
TO DO:
- Include more languages from the benchmark.