# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("Nextcloud-AI/opus-mt-fr-es")
model = AutoModelForSeq2SeqLM.from_pretrained("Nextcloud-AI/opus-mt-fr-es")Quick Links
opus-mt-fr-es
source languages: fr
target languages: es
OPUS readme: fr-es
dataset: opus
model: transformer-align
pre-processing: normalization + SentencePiece
download original weights: opus-2020-01-09.zip
test set translations: opus-2020-01-09.test.txt
test set scores: opus-2020-01-09.eval.txt
Benchmarks
| testset | BLEU | chr-F |
|---|---|---|
| newssyscomb2009.fr.es | 34.3 | 0.601 |
| news-test2008.fr.es | 32.5 | 0.583 |
| newstest2009.fr.es | 31.6 | 0.586 |
| newstest2010.fr.es | 36.5 | 0.616 |
| newstest2011.fr.es | 38.3 | 0.622 |
| newstest2012.fr.es | 38.1 | 0.619 |
| newstest2013.fr.es | 34.0 | 0.587 |
| Tatoeba.fr.es | 53.2 | 0.709 |
- Downloads last month
- 1
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("translation", model="Nextcloud-AI/opus-mt-fr-es")