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

Browse Source
This commit is contained in:
嘉渊 2023-04-25 23:09:58 +08:00
parent 2a3336d9a8
commit 8e5a0d686d
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
egs/aishell/paraformer/run.sh
View File

@ -21,7 +21,7 @@ feats_type=fbank
token_type=char
scp=wav.scp
type=sound
stage=1
stage=2
stop_stage=3
# feature configuration
@ -100,7 +100,7 @@ if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
echo "<blank>" > ${token_list}
echo "<s>" >> ${token_list}
echo "</s>" >> ${token_list}
utils/text2token.py -s 1 -n 1 --space "" ${feats_dir}/data/train/text | cut -f 2- -d" " | tr " " "\n" \
utils/text2token.py -s 1 -n 1 --space "" ${feats_dir}/data/$train_set/text | cut -f 2- -d" " | tr " " "\n" \
| sort | uniq | grep -a -v -e '^\s*$' | awk '{print $0}' >> ${token_list}
echo "<unk>" >> ${token_list}
fi