mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-08-09 18:12:19 +00:00
228 lines
6.2 KiB
Bash
Executable File
228 lines
6.2 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=15
|
|
# run step 0 to step 5 by default
|
|
stage=0
|
|
stop_stage=5
|
|
|
|
# Note: This script just prepare the minimal requirements that needed by a
|
|
# transducer training with bpe units.
|
|
#
|
|
# If you want to use ngram or nnlm, please continue running prepare_lm.sh after
|
|
# you succeed running this script.
|
|
#
|
|
# This script also contains the steps to generate phone based units, but they
|
|
# will not run automatically, you can generate the phone based units by
|
|
# bash prepare.sh --stage -1 --stop-stage -1
|
|
# bash prepare.sh --stage 6 --stop-stage 6
|
|
|
|
|
|
# We assume dl_dir (download dir) contains the following
|
|
# directories and files. If not, they will be downloaded
|
|
# by this script automatically.
|
|
#
|
|
# - $dl_dir/LibriSpeech
|
|
# You can find BOOKS.TXT, test-clean, train-clean-360, etc, inside it.
|
|
# You can download them from https://www.openslr.org/12
|
|
#
|
|
# - $dl_dir/musan
|
|
# This directory contains the following directories downloaded from
|
|
# http://www.openslr.org/17/
|
|
#
|
|
# - music
|
|
# - noise
|
|
# - speech
|
|
|
|
num_per_split=4000
|
|
fbank_dir=data/fbank_mls
|
|
dl_dir=$PWD/download
|
|
|
|
. shared/parse_options.sh || exit 1
|
|
|
|
# vocab size for sentence piece models.
|
|
# It will generate data/lang_bpe_xxx,
|
|
# data/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".
|
|
# 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"
|
|
log "fbank_dir: $fbank_dir"
|
|
|
|
languages=(
|
|
english
|
|
german
|
|
dutch
|
|
spanish
|
|
italian
|
|
french
|
|
polish
|
|
portuguese
|
|
)
|
|
|
|
if [ $stage -le 0 ] && [ $stop_stage -ge 0 ]; then
|
|
log "Stage 0: Download data"
|
|
|
|
# If you have pre-downloaded it to /path/to/MLS,
|
|
# you can create a symlink
|
|
#
|
|
# ln -sfv /path/to/MLS $dl_dir/MLS
|
|
#
|
|
if [ ! -d $dl_dir/MLS/train-other-500 ]; then
|
|
lhotse download mls --full $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 MLS manifest"
|
|
# We assume that you have downloaded the MLS corpus
|
|
# to $dl_dir/MLS
|
|
mkdir -p data/manifests
|
|
if [ ! -e data/manifests/.mls.done ]; then
|
|
lhotse prepare mls -j $nj $dl_dir/MLS data/manifests
|
|
touch data/manifests/.mls.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 $dl_dir/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 ] && [ $stop_stage -ge 3 ]; then
|
|
log "Stage 3: Split english subset into pieces (may take 30 minutes)"
|
|
split_dir=${fbank_dir}/english_split
|
|
if [ ! -f $split_dir/.split_completed ]; then
|
|
lhotse split-lazy ${fbank_dir}/mls-english_train_raw.jsonl.gz $split_dir $num_per_split
|
|
touch $split_dir/.split_completed
|
|
fi
|
|
fi
|
|
|
|
if [ $stage -le 4 ] && [ $stop_stage -ge 4 ]; then
|
|
log "Stage 4: Compute fbank for MLS (except English)"
|
|
mkdir -p ${fbank_dir}
|
|
if [ ! -e ${fbank_dir}/.mls.done ]; then
|
|
./local/compute_fbank_mls.py
|
|
touch ${fbank_dir}/.mls.done
|
|
fi
|
|
fi
|
|
|
|
if [ $stage -le 5 ] && [ $stop_stage -ge 5 ]; then
|
|
log "Stage 5: Compute fbank for English split of MLS"
|
|
if [ ! -e ${fbank_dir}/.mls-english.done ]; then
|
|
num_splits=$(find ${fbank_dir}/english_split -name "mls-english_train_raw.*.jsonl.gz" | wc -l)
|
|
./local/compute_fbank_mls_splits.py \
|
|
--fbank-dir $fbank_dir \
|
|
--num-workers 20 \
|
|
--language english \
|
|
--num-splits $num_splits \
|
|
|
|
touch ${fbank_dir}/.mls-english.done
|
|
fi
|
|
|
|
if [ ! -e ${fbank_dir}/mls-english_train.jsonl.gz ]; then
|
|
pieces=$(find ${fbank_dir}/english_split -name "mls-english_train.*.jsonl.gz")
|
|
lhotse combine $pieces ${fbank_dir}/mls-english_train.jsonl.gz
|
|
fi
|
|
|
|
fi
|
|
|
|
if [ $stage -le 6 ] && [ $stop_stage -ge 6 ]; then
|
|
log "Stage 6: Validate the manifest of MLS"
|
|
if [ ! -e ${fbank_dir}/.mls-validated.done ]; then
|
|
log "Validating the fbank features for MLS"
|
|
parts=(
|
|
train
|
|
dev
|
|
test
|
|
)
|
|
for lan in ${languages[@]}; do
|
|
for part in ${parts[@]}; do
|
|
python3 ./local/validate_manifest.py \
|
|
${fbank_dir}/mls-${lan}_${part}.jsonl.gz
|
|
done
|
|
done
|
|
touch ${fbank_dir}/.mls-validated.done
|
|
fi
|
|
fi
|
|
|
|
if [ $stage -le 7 ] && [ $stop_stage -ge 7 ]; then
|
|
log "Stage 7: Compute fbank for musan"
|
|
mkdir -p ${fbank_dir}
|
|
if [ ! -e ${fbank_dir}/.musan.done ]; then
|
|
./local/compute_fbank_musan.py
|
|
touch ${fbank_dir}/.musan.done
|
|
fi
|
|
fi
|
|
|
|
if [ $stage -le 8 ] && [ $stop_stage -ge 8 ]; then
|
|
log "Stage 8: Prepare BPE based lang"
|
|
|
|
for vocab_size in ${vocab_sizes[@]}; do
|
|
lang_dir=data/lang_bpe_${vocab_size}
|
|
mkdir -p $lang_dir
|
|
|
|
if [ ! -f $lang_dir/transcript_words.txt ]; then
|
|
log "Generate data for BPE training"
|
|
files=(
|
|
"$dl_dir/MLS/mls_english/train/transcripts.txt"
|
|
"$dl_dir/MLS/mls_german/train/transcripts.txt"
|
|
"$dl_dir/MLS/mls_dutch/train/transcripts.txt"
|
|
"$dl_dir/MLS/mls_french/train/transcripts.txt"
|
|
"$dl_dir/MLS/mls_spanish/train/transcripts.txt"
|
|
"$dl_dir/MLS/mls_italian/train/transcripts.txt"
|
|
"$dl_dir/MLS/mls_portuguese/train/transcripts.txt"
|
|
"$dl_dir/MLS/mls_polish/train/transcripts.txt"
|
|
)
|
|
for f in ${files[@]}; do
|
|
head -n 1000000 $f | cut -d " " -f 2-
|
|
done > $lang_dir/transcript_words.txt
|
|
fi
|
|
|
|
if [ ! -f $lang_dir/bpe.model ]; then
|
|
./local/train_bpe_model.py \
|
|
--lang-dir $lang_dir \
|
|
--vocab-size $vocab_size \
|
|
--character-coverage 0.999 \
|
|
--transcript $lang_dir/transcript_words.txt \
|
|
--byte-fallback
|
|
fi
|
|
done
|
|
fi
|
|
|