You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
63 lines
1.9 KiB
63 lines
1.9 KiB
3 years ago
|
#!/bin/bash
|
||
|
|
|
||
|
|
stage=0
|
||
|
|
stop_stage=100
|
||
|
|
|
||
|
|
config_path=$1
|
||
|
|
|
||
|
|
if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
|
||
|
|
# get durations from MFA's result
|
||
|
|
echo "Generate durations.txt from MFA results ..."
|
||
|
|
python3 ${MAIN_ROOT}/utils/gen_duration_from_textgrid.py \
|
||
|
|
--inputdir=./baker_alignment_tone \
|
||
|
|
--output=durations.txt \
|
||
|
|
--config=${config_path}
|
||
|
|
fi
|
||
|
|
|
||
|
|
if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
|
||
|
|
# extract features
|
||
|
|
echo "Extract features ..."
|
||
|
|
python3 ${BIN_DIR}/preprocess.py \
|
||
|
|
--dataset=baker \
|
||
|
|
--rootdir=~/datasets/BZNSYP/ \
|
||
|
|
--dumpdir=dump \
|
||
|
|
--dur-file=durations.txt \
|
||
|
|
--config=${config_path} \
|
||
|
|
--num-cpu=20 \
|
||
|
|
--cut-sil=True
|
||
|
|
fi
|
||
|
|
|
||
|
|
if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
|
||
|
|
# get features' stats(mean and std)
|
||
|
|
echo "Get features' stats ..."
|
||
|
|
python3 ${MAIN_ROOT}/utils/compute_statistics.py \
|
||
|
|
--metadata=dump/train/raw/metadata.jsonl \
|
||
|
|
--field-name="speech"
|
||
|
|
|
||
|
|
fi
|
||
|
|
|
||
|
|
if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
|
||
|
|
# normalize and covert phone to id, dev and test should use train's stats
|
||
|
|
echo "Normalize ..."
|
||
|
|
python3 ${BIN_DIR}/normalize.py \
|
||
|
|
--metadata=dump/train/raw/metadata.jsonl \
|
||
|
|
--dumpdir=dump/train/norm \
|
||
|
|
--speech-stats=dump/train/speech_stats.npy \
|
||
|
|
--phones-dict=dump/phone_id_map.txt \
|
||
|
|
--speaker-dict=dump/speaker_id_map.txt
|
||
|
|
|
||
|
|
python3 ${BIN_DIR}/normalize.py \
|
||
|
|
--metadata=dump/dev/raw/metadata.jsonl \
|
||
|
|
--dumpdir=dump/dev/norm \
|
||
|
|
--speech-stats=dump/train/speech_stats.npy \
|
||
|
|
--phones-dict=dump/phone_id_map.txt \
|
||
|
|
--speaker-dict=dump/speaker_id_map.txt
|
||
|
|
|
||
|
|
python3 ${BIN_DIR}/normalize.py \
|
||
|
|
--metadata=dump/test/raw/metadata.jsonl \
|
||
|
|
--dumpdir=dump/test/norm \
|
||
|
|
--speech-stats=dump/train/speech_stats.npy \
|
||
|
|
--phones-dict=dump/phone_id_map.txt \
|
||
|
|
--speaker-dict=dump/speaker_id_map.txt
|
||
|
|
fi
|