aboutsummaryrefslogtreecommitdiffstats
path: root/get_embeddings.sh
diff options
context:
space:
mode:
Diffstat (limited to 'get_embeddings.sh')
-rwxr-xr-xget_embeddings.sh7
1 files changed, 5 insertions, 2 deletions
diff --git a/get_embeddings.sh b/get_embeddings.sh
index 0c5d918..dde7839 100755
--- a/get_embeddings.sh
+++ b/get_embeddings.sh
@@ -38,6 +38,9 @@ wget -nc -q https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.sl.300.vec.
38echo "Extracting embeddings" 38echo "Extracting embeddings"
39 39
40for LANG in sq bg el it ro sl; do 40for LANG in sq bg el it ro sl; do
41 gunzip -fc "${EMBS}/cc.${LANG}.300.vec.gz" > "${EMBS}/${LANG}.1M.vec" 41 gunzip "${EMBS}/cc.${LANG}.300.vec.gz"
42 rm -f "${EMBS}/cc.${LANG}.300.vec.gz" 42 mv "${EMBS}/cc.${LANG}.300.vec.gz" "${EMBS}/${LANG}.1M.vec"
43done 43done
44
45unzip -ofq "${EMBS}/crawl-300d-2M.vec.zip" -d "${EMBS}"
46mv "${EMBS}/crawl-300d-2M.vec" "${EMBS}/en.vec"