mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-08-26 10:16:14 +00:00
55 lines
1.4 KiB
Bash
Executable File
55 lines
1.4 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=16
|
|
# run step 1 to step 5 by default
|
|
stage=1
|
|
stop_stage=5
|
|
|
|
# We assume dl_dir (download dir) contains the following directories and files.
|
|
#
|
|
# - $dl_dir/GigaSpeech2
|
|
|
|
dl_dir=$PWD/download
|
|
lang=Thai
|
|
|
|
. shared/parse_options.sh || exit 1
|
|
|
|
# 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 "Running prepare.sh"
|
|
|
|
log "dl_dir: $dl_dir"
|
|
|
|
if [ $stage -le 1 ] && [ $stop_stage -ge 1 ]; then
|
|
log "Stage 1: Prepare GigaSpeech2 manifest, language: $lang"
|
|
# We assume that you have downloaded the GigaSpeech2 corpus
|
|
# to $dl_dir/GigaSpeech2
|
|
mkdir -p data/manifests
|
|
if [ ! -e data/manifests/.gigaspeech2.done ]; then
|
|
lhotse prepare gigaspeech2 --lang $lang -j $nj $dl_dir/GigaSpeech2 data/manifests
|
|
touch data/manifests/.gigaspeech2.done
|
|
fi
|
|
fi
|
|
|
|
if [ $stage -le 2 ] && [ $stop_stage -ge 2 ]; then
|
|
log "Stage 2: Compute fbank for gigaspeech2"
|
|
mkdir -p data/fbank
|
|
if [ ! -e data/fbank/.gigaspeech2.done ]; then
|
|
./local/compute_fbank_gigaspeech2.py
|
|
touch data/fbank/.gigaspeech2.done
|
|
fi
|
|
fi
|