Skip to content

Commit

Permalink
Merge pull request #4926 from roshansh-cmu/extracted_fix
Browse files Browse the repository at this point in the history
fix extracted feature dummy generation
  • Loading branch information
sw005320 committed Feb 15, 2023
2 parents 5d4615f + 6fcbfbb commit 78c93bc
Show file tree
Hide file tree
Showing 4 changed files with 30 additions and 6 deletions.
10 changes: 8 additions & 2 deletions egs2/TEMPLATE/asr1/asr.sh
Original file line number Diff line number Diff line change
Expand Up @@ -620,8 +620,14 @@ if ! "${skip_data_prep}"; then
_suf=""
fi
# Generate dummy wav.scp to avoid error by copy_data_dir.sh
<data/"${dset}"/feats.scp awk ' { print($1,"<DUMMY>") }' > data/"${dset}"/wav.scp
utils/copy_data_dir.sh --validate_opts --non-print data/"${dset}" "${data_feats}${_suf}/${dset}"
if [ ! -f data/"${dset}"/wav.scp ]; then
if [ ! -f data/"${dset}"/segments ]; then
<data/"${dset}"/feats.scp awk ' { print($1,"<DUMMY>") }' > data/"${dset}"/wav.scp
else
<data/"${dset}"/segments awk ' { print($2,"<DUMMY>") }' > data/"${dset}"/wav.scp
fi
fi
utils/copy_data_dir.sh --validate_opts --non-print data/"${dset}" "${data_feats}${_suf}/${dset}"

# Copy reference text files if there is more than 1 reference
# shellcheck disable=SC2068
Expand Down
10 changes: 8 additions & 2 deletions egs2/TEMPLATE/slu1/slu.sh
Original file line number Diff line number Diff line change
Expand Up @@ -573,7 +573,13 @@ if ! "${skip_data_prep}"; then
_suf=""
fi
# Generate dummy wav.scp to avoid error by copy_data_dir.sh
<data/"${dset}"/cmvn.scp awk ' { print($1,"<DUMMY>") }' > data/"${dset}"/wav.scp
if [ ! -f data/"${dset}"/wav.scp ]; then
if [ ! -f data/"${dset}"/segments ]; then
<data/"${dset}"/feats.scp awk ' { print($1,"<DUMMY>") }' > data/"${dset}"/wav.scp
else
<data/"${dset}"/segments awk ' { print($2,"<DUMMY>") }' > data/"${dset}"/wav.scp
fi
fi
utils/copy_data_dir.sh --validate_opts --non-print data/"${dset}" "${data_feats}${_suf}/${dset}"

# Derive the the frame length and feature dimension
Expand Down Expand Up @@ -1657,4 +1663,4 @@ else
log "Skip the uploading to HuggingFace stage"
fi

log "Successfully finished. [elapsed=${SECONDS}s]"
log "Successfully finished. [elapsed=${SECONDS}s]"
8 changes: 7 additions & 1 deletion egs2/TEMPLATE/st1/st.sh
Original file line number Diff line number Diff line change
Expand Up @@ -616,7 +616,13 @@ if ! "${skip_data_prep}"; then
_suf=""
fi
# Generate dummy wav.scp to avoid error by copy_data_dir.sh
<data/"${dset}"/cmvn.scp awk ' { print($1,"<DUMMY>") }' > data/"${dset}"/wav.scp
if [ ! -f data/"${dset}"/wav.scp ]; then
if [ ! -f data/"${dset}"/segments ]; then
<data/"${dset}"/feats.scp awk ' { print($1,"<DUMMY>") }' > data/"${dset}"/wav.scp
else
<data/"${dset}"/segments awk ' { print($2,"<DUMMY>") }' > data/"${dset}"/wav.scp
fi
fi
utils/copy_data_dir.sh --validate_opts --non-print data/"${dset}" "${data_feats}${_suf}/${dset}"

# expand the utt_extra_files for multi-references
Expand Down
8 changes: 7 additions & 1 deletion egs2/TEMPLATE/uasr1/uasr.sh
Original file line number Diff line number Diff line change
Expand Up @@ -589,7 +589,13 @@ if ! "${skip_data_prep}"; then
_suf=""
fi
# Generate dummy wav.scp to avoid error by copy_data_dir.sh
<data/"${dset}"/cmvn.scp awk ' { print($1,"<DUMMY>") }' > data/"${dset}"/wav.scp
if [ ! -f data/"${dset}"/wav.scp ]; then
if [ ! -f data/"${dset}"/segments ]; then
<data/"${dset}"/feats.scp awk ' { print($1,"<DUMMY>") }' > data/"${dset}"/wav.scp
else
<data/"${dset}"/segments awk ' { print($2,"<DUMMY>") }' > data/"${dset}"/wav.scp
fi
fi
utils/copy_data_dir.sh --validate_opts --non-print data/"${dset}" "${data_feats}${_suf}/${dset}"

# Derive the the frame length and feature dimension
Expand Down

0 comments on commit 78c93bc

Please sign in to comment.