s434704/synthetic_errors
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Remove screen enable

Browse Source
This commit is contained in:
Wojciech Jarmosz 2022-04-24 21:53:16 +02:00
parent 50c8e173ed
commit 0920f529a1
1 changed files with 1 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
install.sh
View File

@ -12,4 +12,3 @@ mkdir data && cd data
wget https://minio.clarin-pl.eu/ermlab/public/PoLitBert/corpus-oscar/corpus_oscar_2020-04-10_64M_lines.zip
unzip -p corpus_oscar_2020-04-10_64M_lines.zip | sed -r '/^\s*$/d' | gawk 'NF>6' > oscar_filtered.txt
split -l 1000000 --numeric-suffixes=1 --suffix-length=1 --additional-suffix=".txt" oscar_filtered.txt ""
screen -S generate_synt_data