Commit 38f814be authored by Abdelwahab HEBA's avatar Abdelwahab HEBA
Browse files

use parseText for Text extraction from <Transcriber> format

parent ef1e83d8
......@@ -27,8 +27,10 @@ for b in $(cat $in_list); do
echo "Start processing $id at $(date '+%T %F')"
[[ -f "$in_file" ]] || { echo "WARNING: $in_file does not exists"; continue; }
#python3 local/ $b
python3 local/lm/ $in_file |\
$PYTHON local/lm/ /dev/stdin $out_root/corpus_train.txt
$PYTHON local/lm/ /dev/stdin $out_root/$id.txt
#$PYTHON local/lm/ /dev/stdin $out_root/corpus_train.txt
processed=$((processed + 1))
echo "Processing of $id has finished at $(date '+%T %F') [$processed texts ready so far]"
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