Commit f9349a6c authored by Abdelwahab HEBA's avatar Abdelwahab HEBA
Browse files

replace <UNK> with <unk> in score.sh

parent 3ad59a3d
...@@ -55,7 +55,7 @@ done ...@@ -55,7 +55,7 @@ done
for wip in $(echo $word_ins_penalty | sed 's/,/ /g'); do for wip in $(echo $word_ins_penalty | sed 's/,/ /g'); do
$cmd LMWT=$min_lmwt:$max_lmwt $dir/scoring/log/score.LMWT.$wip.log \ $cmd LMWT=$min_lmwt:$max_lmwt $dir/scoring/log/score.LMWT.$wip.log \
cat $dir/scoring/LMWT.$wip.tra \| \ cat $dir/scoring/LMWT.$wip.tra \| \
utils/int2sym.pl -f 2- $symtab \| sed 's:\<UNK\>::g' \| \ utils/int2sym.pl -f 2- $symtab \| sed 's:\<unk\>::g' \| \
compute-wer --text --mode=present \ compute-wer --text --mode=present \
ark:$dir/scoring/test_filt.txt ark,p:- ">&" $dir/wer_LMWT_$wip || exit 1; ark:$dir/scoring/test_filt.txt ark,p:- ">&" $dir/wer_LMWT_$wip || exit 1;
done done
......
...@@ -18,6 +18,7 @@ LM_train_text=/home/lingora/Documents/Linagora/Data/Tcof/tcof/3/Corpus/train ...@@ -18,6 +18,7 @@ LM_train_text=/home/lingora/Documents/Linagora/Data/Tcof/tcof/3/Corpus/train
#train dev #train dev
for part in dev test train ; do for part in dev test train ; do
# use underscore-separated names in data directories. # use underscore-separated names in data directories.
echo "prep $part"
local/data_prep.sh $data/$part data/$part local/data_prep.sh $data/$part data/$part
done done
###### OOOOOK ###### OOOOOK
...@@ -52,7 +53,7 @@ local/prepare_dict.sh --stage 3 --nj 4 --cmd "$train_cmd" \ ...@@ -52,7 +53,7 @@ local/prepare_dict.sh --stage 3 --nj 4 --cmd "$train_cmd" \
###### OOOOOOK ###### OOOOOOK
utils/prepare_lang.sh data/local/dict \ utils/prepare_lang.sh data/local/dict \
"<UNK>" data/local/lang_tmp data/lang "<unk>" data/local/lang_tmp data/lang
export LC_ALL=fr_FR.UTF-8 export LC_ALL=fr_FR.UTF-8
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment