[scripts] subset_data_dir.sh: preserve the comments in STM file (kald…

…i-asr#2627)
desh2608 · Aug 18, 2018 · c999329 · c999329
1 parent bba22b5
commit c999329
Showing 1 changed file with 4 additions and 2 deletions.
diff --git a/egs/wsj/s5/utils/subset_data_dir.sh b/egs/wsj/s5/utils/subset_data_dir.sh
@@ -124,8 +124,10 @@ function do_filtering {
      [ -f $srcdir/reco2file_and_channel ] && \
        utils/filter_scp.pl $destdir/reco <$srcdir/reco2file_and_channel >$destdir/reco2file_and_channel
 
-     # Filter the STM file for proper sclite scoring (this will also remove the comments lines)
-     [ -f $srcdir/stm ] && utils/filter_scp.pl $destdir/reco < $srcdir/stm > $destdir/stm
+     # Filter the STM file for proper sclite scoring
+     # Copy over the comments from STM file
+     [ -f $srcdir/stm ] && grep "^;;" $srcdir/stm > $destdir/stm
+     [ -f $srcdir/stm ] && utils/filter_scp.pl $destdir/reco < $srcdir/stm >> $destdir/stm
 
      rm $destdir/reco
   else