Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 11 additions & 1 deletion egs/wsj/s5/utils/fix_data_dir.sh
Original file line number Diff line number Diff line change
Expand Up @@ -155,12 +155,22 @@ function filter_utts {
maybe_reco2dur=
[ ! -f $data/segments ] && maybe_wav=wav.scp # wav indexed by utts only if segments does not exist.
[ -s $data/reco2dur ] && [ ! -f $data/segments ] && maybe_reco2dur=reco2dur # reco2dur indexed by utts
for x in feats.scp text segments utt2lang $maybe_wav; do

maybe_utt2dur=
if [ -f $data/utt2dur ]; then
cat $data/utt2dur | \
awk '{ if (NF == 2 && $2 > 0) { print }}' > $data/utt2dur.ok || exit 1
maybe_utt2dur=utt2dur.ok
fi

for x in feats.scp text segments utt2lang $maybe_wav $maybe_utt2dur; do
if [ -f $data/$x ]; then
utils/filter_scp.pl $data/$x $tmpdir/utts > $tmpdir/utts.tmp
mv $tmpdir/utts.tmp $tmpdir/utts
fi
done
rm $data/utt2dur.ok 2>/dev/null || true

[ ! -s $tmpdir/utts ] && echo "fix_data_dir.sh: no utterances remained: not proceeding further." && \
rm $tmpdir/utts && exit 1;

Expand Down