OPUS Multilingual Translation Models
Collection
English-to-German, Spanish, Hindi, and Chinese neural machine translation checkpoints and parallel corpus. โข 5 items โข Updated
How to use entity2260/opus_en_es with Transformers:
# 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="entity2260/opus_en_es") # pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("entity2260/opus_en_es", device_map="auto")Configuration Parsing Warning:Invalid JSON for config file config.json
Configuration Parsing Warning:Invalid JSON for config file tokenizer_config.json
source group: English
target group: Spanish
OPUS readme: eng-spa
model: transformer
source language(s): eng
target language(s): spa
model: transformer
pre-processing: normalization + SentencePiece (spm32k,spm32k)
download original weights: opus-2020-08-18.zip
test set translations: opus-2020-08-18.test.txt
test set scores: opus-2020-08-18.eval.txt