-
source language name: Czech
-
target language name: Ukrainian
-
-
model: transformer-align
-
source language code: cs
-
target language code: uk
-
dataset: opus
-
release date: 2021-02-18
-
pre-processing: normalization + SentencePiece (spm32k,spm32k)
-
download original weights:
opus-2021-02-18.zip
-
Training data:
- ces-ukr: Tatoeba-train (1635823)
-
Validation data:
- ces-ukr: Tatoeba-dev, 1000
- total-size-shuffled: 1000
- devset-selected: top 1000 lines of Tatoeba-dev.src.shuffled!
-
Test data:
- Tatoeba-test.ces-ukr: 1787/8891
-
test set translations file:
test.txt
-
test set scores file:
eval.txt
-
BLEU-scores
|Test set|score|
|---|---|
|Tatoeba-test.ces-ukr|50.9|
-
chr-F-scores
|Test set|score|
|---|---|
|Tatoeba-test.ces-ukr|0.68|