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.
52 lines
1.1 KiB
52 lines
1.1 KiB
#! /usr/bin/env bash
|
|
|
|
cd ../.. > /dev/null
|
|
|
|
# prepare folder
|
|
if [ ! -e data/tiny ]; then
|
|
mkdir data/tiny
|
|
fi
|
|
|
|
|
|
# download data, generate manifests
|
|
PYTHONPATH=.:$PYTHONPATH python data/librispeech/librispeech.py \
|
|
--manifest_prefix='data/tiny/manifest' \
|
|
--target_dir='~/.cache/paddle/dataset/speech/libri' \
|
|
--full_download='False'
|
|
|
|
if [ $? -ne 0 ]; then
|
|
echo "Prepare LibriSpeech failed. Terminated."
|
|
exit 1
|
|
fi
|
|
|
|
head -n 64 data/tiny/manifest.dev-clean > data/tiny/manifest.tiny
|
|
|
|
|
|
# build vocabulary
|
|
python tools/build_vocab.py \
|
|
--count_threshold=0 \
|
|
--vocab_path='data/tiny/vocab.txt' \
|
|
--manifest_paths='data/tiny/manifest.dev-clean'
|
|
|
|
if [ $? -ne 0 ]; then
|
|
echo "Build vocabulary failed. Terminated."
|
|
exit 1
|
|
fi
|
|
|
|
|
|
# compute mean and stddev for normalizer
|
|
python tools/compute_mean_std.py \
|
|
--manifest_path='data/tiny/manifest.tiny' \
|
|
--num_samples=64 \
|
|
--specgram_type='linear' \
|
|
--output_path='data/tiny/mean_std.npz'
|
|
|
|
if [ $? -ne 0 ]; then
|
|
echo "Compute mean and stddev failed. Terminated."
|
|
exit 1
|
|
fi
|
|
|
|
|
|
echo "Tiny data preparation done."
|
|
exit 0
|