# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-de-cs")
model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-de-cs", device_map="auto")Quick Links
opus-mt-de-cs
source languages: de
target languages: cs
OPUS readme: de-cs
dataset: opus
model: transformer-align
pre-processing: normalization + SentencePiece
download original weights: opus-2020-01-20.zip
test set translations: opus-2020-01-20.test.txt
test set scores: opus-2020-01-20.eval.txt
Benchmarks
| testset | BLEU | chr-F |
|---|---|---|
| newssyscomb2009.de.cs | 22.4 | 0.499 |
| news-test2008.de.cs | 20.2 | 0.487 |
| newstest2009.de.cs | 20.9 | 0.485 |
| newstest2010.de.cs | 22.7 | 0.510 |
| newstest2011.de.cs | 21.2 | 0.487 |
| newstest2012.de.cs | 20.9 | 0.479 |
| newstest2013.de.cs | 23.0 | 0.500 |
| newstest2019-decs.de.cs | 22.5 | 0.495 |
| Tatoeba.de.cs | 42.2 | 0.625 |
- Downloads last month
- 198
# 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="Helsinki-NLP/opus-mt-de-cs")