diff options
| author | Marcin Junczys-Dowmunt <junczys@amu.edu.pl> | 2017-03-25 13:44:24 +0300 |
|---|---|---|
| committer | Marcin Junczys-Dowmunt <junczys@amu.edu.pl> | 2017-03-25 13:44:24 +0300 |
| commit | 274a3b4741b8931123052dad42184047c36e2c41 (patch) | |
| tree | 0c55b617f7aba93a542908f64a718cc321383445 /examples/training | |
| parent | 463da37570ce4e815745ee8f09ac80d70dc38531 (diff) | |
download back-translated files
Diffstat (limited to 'examples/training')
| -rwxr-xr-x | examples/training/scripts/download-files.sh | 11 |
1 files changed, 9 insertions, 2 deletions
diff --git a/examples/training/scripts/download-files.sh b/examples/training/scripts/download-files.sh index 069dcbc2..9a739a60 100755 --- a/examples/training/scripts/download-files.sh +++ b/examples/training/scripts/download-files.sh @@ -12,11 +12,18 @@ then wget http://opus.lingfil.uu.se/download.php?f=SETIMES2/en-ro.txt.zip -O data/SETIMES2.ro-en.txt.zip fi +if [ ! -f data/corpus.bt.ro-en.en.gz ]; +then + wget http://data.statmt.org/rsennrich/wmt16_backtranslations/ro-en/corpus.bt.ro-en.en.gz -O data/corpus.bt.ro-en.en.gz + wget http://data.statmt.org/rsennrich/wmt16_backtranslations/ro-en/corpus.bt.ro-en.ro.gz -O data/corpus.bt.ro-en.ro.gz +fi + cd data/ tar -xf ro-en.tgz unzip SETIMES2.ro-en.txt.zip +gzip -d corpus.bt.ro-en.en.gz corpus.bt.ro-en.ro.gz -cat europarl-v7.ro-en.en SETIMES2.en-ro.en > corpus.en -cat europarl-v7.ro-en.ro SETIMES2.en-ro.ro > corpus.ro +cat europarl-v7.ro-en.en SETIMES2.en-ro.en corpus.bt.ro-en.en > corpus.en +cat europarl-v7.ro-en.ro SETIMES2.en-ro.ro corpus.bt.ro-en.ro > corpus.ro cd .. |