Downloads · 30 days
10
26% of all-time downloads
translate-glg-cat
softcatala/translate-glg-cat
translate-glg-cat is a translation model from softcatala. Use it when you need text moved from one language to another. It is set up for opennmt. The card lists the license as mit.
Galician - Catalan translation model based on OpenNMT. These are the same models that we have in production at https://www.softcatala.org/traductor/.
All-time downloads
39
Public
Repo size
144 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin70.7 MB · 97%
At a glance
- Task
- Translation
- Library
- opennmt
- License
- mit
- Access
- Public
- Created
- Aug 19, 2024
- Updated
- Sep 9, 2024
- SHA
- f353e751
Model card
From the Hugging Face model README
Introduction
Galician - 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-glg-cat", revision="main")
tokenizer=pyonmttok.Tokenizer(mode="none", sp_model_path = model_dir + "/sp_m.model")
tokenized=tokenizer.tokenize("Bom día a todos")
import ctranslate2
translator = ctranslate2.Translator(model_dir)
translated = translator.translate_batch([tokenized[0]])
print(tokenizer.detokenize(translated[0][0]['tokens']))
Benchmarks
| testset | BLEU |
|---|---|
| test dataset (from train/dev/test) | 66.4 |
| Flores200 dataset | 32.5 |
Additional information
- Task
- Translation
- Library
- opennmt
- License
- mit
- Languages
- ca, gl
- Created
- Aug 19, 2024
- Updated
- Sep 9, 2024