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 22:33:45 +08:00
parent 9f032d0f08
commit a12f5382e9
1 changed files with 2 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
egs/aishell/paraformer/run.sh
View File

@ -21,14 +21,12 @@ feats_type=fbank
token_type=char token_type=char
scp=wav.scp scp=wav.scp
type=sound type=sound
stage=1 stage=2
stop_stage=1 stop_stage=2
# feature configuration # feature configuration
feats_dim=80 feats_dim=80
sample_frequency=16000
nj=64 nj=64
speed_perturb="0.9,1.0,1.1"
# data # data
raw_data= raw_data=
@ -104,9 +102,7 @@ if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
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 "" ${feats_dir}/data/train/text | cut -f 2- -d" " | tr " " "\n" \
| sort | uniq | grep -a -v -e '^\s*$' | awk '{print $0}' >> ${token_list} | sort | uniq | grep -a -v -e '^\s*$' | awk '{print $0}' >> ${token_list}
num_token=$(cat ${token_list} | wc -l)
echo "<unk>" >> ${token_list} echo "<unk>" >> ${token_list}
vocab_size=$(cat ${token_list} | wc -l)
fi fi
# Training Stage # Training Stage