speech_recognition/FunASR
1
0
Fork 0
mirror of https://github.com/modelscope/FunASR synced 2025-09-15 14:48:36 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

update repo

Browse Source
This commit is contained in:
嘉渊 2023-05-10 19:32:52 +08:00
parent c5b15732d4
commit 65f9d10fdb
1 changed files with 1 additions and 28 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
egs/librispeech_100h/conformer/local/data_prep.sh
View File

@ -29,8 +29,6 @@ mkdir -p $dst || exit 1
wav_scp=$dst/wav.scp; [[ -f "$wav_scp" ]] && rm $wav_scp
trans=$dst/text; [[ -f "$trans" ]] && rm $trans
utt2spk=$dst/utt2spk; [[ -f "$utt2spk" ]] && rm $utt2spk
spk2gender=$dst/spk2gender; [[ -f $spk2gender ]] && rm $spk2gender
for reader_dir in $(find -L $src -mindepth 1 -maxdepth 1 -type d | sort); do
reader=$(basename $reader_dir)
@ -39,12 +37,6 @@ for reader_dir in $(find -L $src -mindepth 1 -maxdepth 1 -type d | sort); do
exit 1
fi
reader_gender=$(egrep "^$reader[ ]+\|" $spk_file | awk -F'|' '{gsub(/[ ]+/, ""); print tolower($2)}')
if [ "$reader_gender" != 'm' ] && [ "$reader_gender" != 'f' ]; then
echo "Unexpected gender: '$reader_gender'"
exit 1
fi
for chapter_dir in $(find -L $reader_dir/ -mindepth 1 -maxdepth 1 -type d | sort); do
chapter=$(basename $chapter_dir)
if ! [ "$chapter" -eq "$chapter" ]; then
@ -53,33 +45,14 @@ for reader_dir in $(find -L $src -mindepth 1 -maxdepth 1 -type d | sort); do
fi
find -L $chapter_dir/ -iname "*.flac" | sort | xargs -I% basename % .flac | \
awk -v "dir=$chapter_dir" '{printf "%s flac -c -d -s %s/%s.flac |\n", $0, dir, $0}' >>$wav_scp|| exit 1
awk -v "dir=$chapter_dir" '{printf "%s %s/%s.flac \n", $0, dir, $0}' >>$wav_scp|| exit 1
chapter_trans=$chapter_dir/${reader}-${chapter}.trans.txt
[ ! -f $chapter_trans ] && echo "$0: expected file $chapter_trans to exist" && exit 1
cat $chapter_trans >>$trans
# NOTE: For now we are using per-chapter utt2spk. That is each chapter is considered
# to be a different speaker. This is done for simplicity and because we want
# e.g. the CMVN to be calculated per-chapter
awk -v "reader=$reader" -v "chapter=$chapter" '{printf "%s %s-%s\n", $1, reader, chapter}' \
<$chapter_trans >>$utt2spk || exit 1
# reader -> gender map (again using per-chapter granularity)
echo "${reader}-${chapter} $reader_gender" >>$spk2gender
done
done
spk2utt=$dst/spk2utt
utils/utt2spk_to_spk2utt.pl <$utt2spk >$spk2utt || exit 1
ntrans=$(wc -l <$trans)
nutt2spk=$(wc -l <$utt2spk)
! [ "$ntrans" -eq "$nutt2spk" ] && \
echo "Inconsistent #transcripts($ntrans) and #utt2spk($nutt2spk)" && exit 1
utils/validate_data_dir.sh --no-feats $dst || exit 1
echo "$0: successfully prepared data in $dst"
exit 0