mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-12-11 06:55:27 +00:00
109 lines
2.6 KiB
Bash
Executable File
109 lines
2.6 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
|
|
# fix segmentation fault reported in https://github.com/k2-fsa/icefall/issues/674
|
|
export PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION=python
|
|
|
|
set -eou pipefail
|
|
|
|
nj=10
|
|
stage=-1
|
|
stop_stage=100
|
|
|
|
version=v1.0
|
|
tgt_lang=de
|
|
dl_dir=$PWD/download
|
|
|
|
must_c_dir=$dl_dir/must-c/$version/en-$tgt_lang/data
|
|
|
|
# We assume dl_dir (download dir) contains the following
|
|
# directories and files.
|
|
# - $dl_dir/must-c/$version/en-$tgt_lang/data/{dev,train,tst-COMMON,tst-HE}
|
|
#
|
|
# Please go to https://ict.fbk.eu/must-c-releases/
|
|
# to download and untar the dataset if you have not already done this.
|
|
|
|
# - $dl_dir/musan
|
|
# This directory contains the following directories downloaded from
|
|
# http://www.openslr.org/17/
|
|
#
|
|
# - music
|
|
# - noise
|
|
# - speech
|
|
|
|
. shared/parse_options.sh || exit 1
|
|
|
|
# vocab size for sentence piece models.
|
|
# It will generate
|
|
# data/lang_bpe_${tgt_lang}_xxx
|
|
# data/lang_bpe_${tgt_lang}_yyy
|
|
# if the array contains xxx, yyy
|
|
vocab_sizes=(
|
|
# 5000
|
|
# 2000
|
|
# 1000
|
|
500
|
|
)
|
|
|
|
# All files generated by this script are saved in "data".
|
|
# You can safely remove "data" and rerun this script to regenerate it.
|
|
mkdir -p data
|
|
|
|
log() {
|
|
# This function is from espnet
|
|
local fname=${BASH_SOURCE[1]##*/}
|
|
echo -e "$(date '+%Y-%m-%d %H:%M:%S') (${fname}:${BASH_LINENO[0]}:${FUNCNAME[1]}) $*"
|
|
}
|
|
|
|
log "dl_dir: $dl_dir"
|
|
|
|
if [ ! -d $must_c_dir ]; then
|
|
log "$must_c_dir does not exist"
|
|
exit 1
|
|
fi
|
|
|
|
for d in dev train tst-COMMON tst-HE; do
|
|
if [ ! -d $must_c_dir/$d ]; then
|
|
log "$must_c_dir/$d does not exist!"
|
|
exit 1
|
|
fi
|
|
done
|
|
|
|
if [ $stage -le 0 ] && [ $stop_stage -ge 0 ]; then
|
|
log "Stage 0: Download musan"
|
|
if [ ! -d $dl_dir/musan ]; then
|
|
lhotse download musan $dl_dir
|
|
fi
|
|
fi
|
|
|
|
if [ $stage -le 1 ] && [ $stop_stage -ge 1 ]; then
|
|
log "Stage 1: Prepare musan manifest"
|
|
# We assume that you have downloaded the musan corpus
|
|
# to data/musan
|
|
mkdir -p data/manifests
|
|
if [ ! -e data/manifests/.musan.done ]; then
|
|
lhotse prepare musan $dl_dir/musan data/manifests
|
|
touch data/manifests/.musan.done
|
|
fi
|
|
fi
|
|
|
|
if [ $stage -le 2 ] && [ $stop_stage -ge 2 ]; then
|
|
log "Stage 2: Prepare must-c $version manifest for target language $tgt_lang"
|
|
mkdir -p data/manifests/$version
|
|
if [ ! -e data/manifests/$version/.done ]; then
|
|
lhotse prepare must-c \
|
|
-j $nj \
|
|
--tgt-lang $tgt_lang \
|
|
$dl_dir/must-c/$version/ \
|
|
data/manifests/$version/
|
|
|
|
touch data/manifests/$version/.done
|
|
fi
|
|
fi
|
|
|
|
if [ $stage -le 3 ] && [ $stop_stage -ge 3 ]; then
|
|
log "Stage 3: Text normalization"
|
|
./local/preprocess_must_c.py \
|
|
--manifest-dir ./data/manifests/$version/ \
|
|
--tgt-lang $tgt_lang
|
|
fi
|