Edit model card

Introduction

French - Catalan translation model based on OpenNMT. These are the same models that we have in production at https://www.softcatala.org/traductor/.

Usage

pip3 install ctranslate2 pyonmttok

Simple translation using Python:

import ctranslate2
import pyonmttok
from huggingface_hub import snapshot_download
model_dir = snapshot_download(repo_id="softcatala/translate-fra-cat", revision="main")

tokenizer=pyonmttok.Tokenizer(mode="none", sp_model_path = model_dir + "/sp_m.model")
tokenized=tokenizer.tokenize("Salut monde")

import ctranslate2
translator = ctranslate2.Translator(model_dir)
translated = translator.translate_batch([tokenized[0]])
print(tokenizer.detokenize(translated[0][0]['tokens']))
Hola món!

Benchmarks

testset BLEU
test dataset (from train/dev/test) 41.3
Flores200 dataset 31.6

Additional information

Downloads last month
6
Inference API
Inference API (serverless) has been turned off for this model.