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.
PaddleSpeech/examples/callcenter/s1/local/data.sh

78 lines
1.9 KiB

3 years ago
#! /usr/bin/env bash
stage=-1
stop_stage=100
source ${MAIN_ROOT}/utils/parse_options.sh
mkdir -p data
if [ ${stage} -le -1 ] && [ ${stop_stage} -ge -1 ]; then
for dataset in train dev test; do
mv data/manifest.${dataset} data/manifest.${dataset}.raw
done
fi
if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
# download data, generate manifests
# build vocabulary
python3 ${MAIN_ROOT}/utils/build_vocab.py \
--unit_type="char" \
--count_threshold=0 \
--vocab_path="data/vocab.txt" \
--manifest_paths "data/manifest.train.raw"
if [ $? -ne 0 ]; then
echo "Build vocabulary failed. Terminated."
exit 1
fi
fi
if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
# compute mean and stddev for normalizer
num_workers=$(nproc)
python3 ${MAIN_ROOT}/utils/compute_mean_std.py \
--manifest_path="data/manifest.train.raw" \
--spectrum_type="fbank" \
3 years ago
--feat_dim=80 \
--delta_delta=false \
--stride_ms=10.0 \
--window_ms=25.0 \
--sample_rate=8000 \
--use_dB_normalization=False \
--num_samples=-1 \
--num_workers=${num_workers} \
--output_path="data/mean_std.json"
if [ $? -ne 0 ]; then
echo "Compute mean and stddev failed. Terminated."
exit 1
fi
fi
if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
# format manifest with tokenids, vocab size
for dataset in train dev test; do
{
python3 ${MAIN_ROOT}/utils/format_data.py \
--feat_type "raw" \
--cmvn_path "data/mean_std.json" \
--unit_type "char" \
--vocab_path="data/vocab.txt" \
--manifest_path="data/manifest.${dataset}.raw" \
--output_path="data/manifest.${dataset}"
if [ $? -ne 0 ]; then
echo "Formt mnaifest failed. Terminated."
exit 1
fi
} &
done
wait
fi
echo "data preparation done."
exit 0