mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-08-08 09:32:20 +00:00
3cb0a0121b
* Add commonvoice * Add data preparation recipe * Updata * update prepare.sh * Fix for black * Update prefix with cv- * 20 -> * Update compute_fbank_commonvoice_dev_test.py * Update prepare.sh * Update compute_fbank_commonvoice_dev_test.py
157 lines
4.4 KiB
Bash
Executable File
157 lines
4.4 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
|
|
set -eou pipefail
|
|
|
|
nj=16
|
|
stage=-1
|
|
stop_stage=100
|
|
|
|
# Split data/${lang}set to this number of pieces
|
|
# This is to avoid OOM during feature extraction.
|
|
num_splits=1000
|
|
|
|
# We assume dl_dir (download dir) contains the following
|
|
# directories and files. If not, they will be downloaded
|
|
# by this script automatically.
|
|
#
|
|
# - $dl_dir/$release/$lang
|
|
# This directory contains the following files downloaded from
|
|
# https://mozilla-common-voice-datasets.s3.dualstack.us-west-2.amazonaws.com/${release}/${release}-${lang}.tar.gz
|
|
#
|
|
# - clips
|
|
# - dev.tsv
|
|
# - invalidated.tsv
|
|
# - other.tsv
|
|
# - reported.tsv
|
|
# - test.tsv
|
|
# - train.tsv
|
|
# - validated.tsv
|
|
#
|
|
# - $dl_dir/musan
|
|
# This directory contains the following directories downloaded from
|
|
# http://www.openslr.org/17/
|
|
#
|
|
# - music
|
|
# - noise
|
|
# - speech
|
|
|
|
dl_dir=$PWD/download
|
|
release=cv-corpus-13.0-2023-03-09
|
|
lang=en
|
|
|
|
. shared/parse_options.sh || exit 1
|
|
|
|
# vocab size for sentence piece models.
|
|
# It will generate data/${lang}/lang_bpe_xxx,
|
|
# data/${lang}/lang_bpe_yyy if the array contains xxx, yyy
|
|
vocab_sizes=(
|
|
# 5000
|
|
# 2000
|
|
# 1000
|
|
500
|
|
)
|
|
|
|
# All files generated by this script are saved in "data/${lang}".
|
|
# You can safely remove "data/${lang}" and rerun this script to regenerate it.
|
|
mkdir -p data/${lang}
|
|
|
|
log() {
|
|
# This function is from espnet
|
|
local fname=${BASH_SOURCE[1]##*/}
|
|
echo -e "$(date '+%Y-%m-%d %H:%M:%S') (${fname}:${BASH_LINENO[0]}:${FUNCNAME[1]}) $*"
|
|
}
|
|
|
|
log "dl_dir: $dl_dir"
|
|
|
|
if [ $stage -le 0 ] && [ $stop_stage -ge 0 ]; then
|
|
log "Stage 0: Download data"
|
|
|
|
# If you have pre-downloaded it to /path/to/$release,
|
|
# you can create a symlink
|
|
#
|
|
# ln -sfv /path/to/$release $dl_dir/$release
|
|
#
|
|
if [ ! -d $dl_dir/$release/$lang/clips ]; then
|
|
lhotse download commonvoice --languages $lang --release $release $dl_dir
|
|
fi
|
|
|
|
# If you have pre-downloaded it to /path/to/musan,
|
|
# you can create a symlink
|
|
#
|
|
# ln -sfv /path/to/musan $dl_dir/
|
|
#
|
|
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 CommonVoice manifest"
|
|
# We assume that you have downloaded the CommonVoice corpus
|
|
# to $dl_dir/$release
|
|
mkdir -p data/${lang}/manifests
|
|
if [ ! -e data/${lang}/manifests/.cv-${lang}.done ]; then
|
|
lhotse prepare commonvoice --language $lang -j $nj $dl_dir/$release data/${lang}/manifests
|
|
touch data/${lang}/manifests/.cv-${lang}.done
|
|
fi
|
|
fi
|
|
|
|
if [ $stage -le 2 ] && [ $stop_stage -ge 2 ]; then
|
|
log "Stage 2: 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 3 ] && [ $stop_stage -ge 3 ]; then
|
|
log "Stage 3: Preprocess CommonVoice manifest"
|
|
if [ ! -e data/${lang}/fbank/.preprocess_complete ]; then
|
|
./local/preprocess_commonvoice.py --language $lang
|
|
touch data/${lang}/fbank/.preprocess_complete
|
|
fi
|
|
fi
|
|
|
|
if [ $stage -le 4 ] && [ $stop_stage -ge 4 ]; then
|
|
log "Stage 4: Compute fbank for dev and test subsets of CommonVoice"
|
|
mkdir -p data/${lang}/fbank
|
|
if [ ! -e data/${lang}/fbank/.cv-${lang}_dev_test.done ]; then
|
|
./local/compute_fbank_commonvoice_dev_test.py --language $lang
|
|
touch data/${lang}/fbank/.cv-${lang}_dev_test.done
|
|
fi
|
|
fi
|
|
|
|
if [ $stage -le 5 ] && [ $stop_stage -ge 5 ]; then
|
|
log "Stage 5: Split train subset into ${num_splits} pieces"
|
|
split_dir=data/${lang}/fbank/train_split_${num_splits}
|
|
if [ ! -e $split_dir/.cv-${lang}_train_split.done ]; then
|
|
lhotse split $num_splits ./data/${lang}/fbank/cv-${lang}_cuts_train_raw.jsonl.gz $split_dir
|
|
touch $split_dir/.cv-${lang}_train_split.done
|
|
fi
|
|
fi
|
|
|
|
if [ $stage -le 6 ] && [ $stop_stage -ge 6 ]; then
|
|
log "Stage 6: Compute features for train subset of CommonVoice"
|
|
if [ ! -e data/${lang}/fbank/.cv-${lang}_train.done ]; then
|
|
./local/compute_fbank_commonvoice_splits.py \
|
|
--num-workers $nj \
|
|
--batch-duration 600 \
|
|
--start 0 \
|
|
--num-splits $num_splits \
|
|
--language $lang
|
|
touch data/${lang}/fbank/.cv-${lang}_train.done
|
|
fi
|
|
fi
|
|
|
|
if [ $stage -le 7 ] && [ $stop_stage -ge 7 ]; then
|
|
log "Stage 7: Compute fbank for musan"
|
|
mkdir -p data/fbank
|
|
if [ ! -e data/fbank/.musan.done ]; then
|
|
./local/compute_fbank_musan.py
|
|
touch data/fbank/.musan.done
|
|
fi
|
|
fi
|