Introduction
Occitan (Languedocian variant) - 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-oci-cat", revision="main")
tokenizer=pyonmttok.Tokenizer(mode="none", sp_model_path = model_dir + "/sp_m.model")
tokenized=tokenizer.tokenize("Hola amics")
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) | 74.9 |
Flores200 dataset | 32.5 |
Additional information
- Downloads last month
- 1