mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-08-29 11:44:18 +00:00
227 lines
6.2 KiB
Bash
227 lines
6.2 KiB
Bash
#!/usr/bin/env bash
|
|
|
|
set -eou pipefail
|
|
|
|
nj=15
|
|
stage=-1
|
|
stop_stage=100
|
|
|
|
# We assume dl_dir (download dir) contains the following
|
|
# directories and files. If not, they will be downloaded
|
|
# by this script automatically.
|
|
#
|
|
# - $dl_dir/tedlium3
|
|
# You can find data, doc, legacy, LM, etc, inside it.
|
|
# You can download them from https://www.openslr.org/51
|
|
#
|
|
# - $dl_dir/lm
|
|
# This directory contains the language model(LM) downloaded from
|
|
# https://huggingface.co/luomingshuang/tedlium3_lm. About how to get these LM files, you can know it
|
|
# from https://github.com/luomingshuang/Train_LM_with_kaldilm.
|
|
#
|
|
# - lm_3_gram.arpa
|
|
# - lm_4_gram.arpa
|
|
#
|
|
# - $dl_dir/musan
|
|
# This directory contains the following directories downloaded from
|
|
# http://www.openslr.org/17/
|
|
#
|
|
# - music
|
|
# - noise
|
|
# - speech
|
|
dl_dir=$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 "dl_dir: $dl_dir"
|
|
|
|
if [ $stage -le -1 ] && [ $stop_stage -ge -1 ]; then
|
|
log "Stage -1: Download LM"
|
|
[ ! -e $dl_dir/lm ] && mkdir -p $dl_dir/lm
|
|
./local/download_lm.py --out-dir=$dl_dir/lm
|
|
fi
|
|
|
|
if [ $stage -le 0 ] && [ $stop_stage -ge 0 ]; then
|
|
log "Stage 0: Download data"
|
|
|
|
# If you have pre-downloaded it to /path/to/LibriSpeech,
|
|
# you can create a symlink
|
|
#
|
|
# ln -sfv /path/to/tedlium3 $dl_dir/tedlium3
|
|
#
|
|
if [ ! -d $dl_dir/tedlium ]; then
|
|
lhotse download tedlium $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/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 tedlium3 manifest"
|
|
# We assume that you have downloaded the tedlium3 corpus
|
|
# to $dl_dir/tedlium3
|
|
mkdir -p data/manifests
|
|
lhotse prepare tedlium $dl_dir/tedlium3 data/manifests
|
|
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
|
|
lhotse prepare musan $dl_dir/musan data/manifests
|
|
fi
|
|
|
|
if [ $stage -le 3 ] && [ $stop_stage -ge 3 ]; then
|
|
log "Stage 3: Compute fbank for tedlium3"
|
|
mkdir -p data/fbank
|
|
./local/compute_fbank_tedlium.py
|
|
fi
|
|
|
|
if [ $stage -le 4 ] && [ $stop_stage -ge 4 ]; then
|
|
log "Stage 4: Compute fbank for musan"
|
|
mkdir -p data/fbank
|
|
./local/compute_fbank_musan.py
|
|
fi
|
|
|
|
if [ $stage -le 5 ] && [ $stop_stage -ge 5 ]; then
|
|
log "Stage 5: Prepare phone based lang"
|
|
lang_dir=data/lang_phone
|
|
mkdir -p $lang_dir
|
|
|
|
if [ ! -f $lang_dir/train.text ]; then
|
|
./local/prepare_transcripts.py \
|
|
--lang-dir $lang_dir \
|
|
--manifests-dir data/manifests
|
|
|
|
cat download/tedlium3/TEDLIUM.152k.dic | grep -v -w "<s>" | grep -v -w "</s>" | grep -v -w "<unk>" | LANG= LC_ALL= sort | sed 's:([0-9])::g' > $lang_dir/lexicon_words.txt
|
|
|
|
(echo '<UNK> <UNK>'; ) |
|
|
cat - $lang_dir/lexicon_words.txt |
|
|
sort | uniq > $lang_dir/lexicon.txt
|
|
|
|
if [ ! -f $lang_dir/L_disambig.pt ]; then
|
|
./local/prepare_lang.py --lang-dir $lang_dir
|
|
fi
|
|
fi
|
|
|
|
if [ $stage -le 6 ] && [ $stop_stage -ge 6 ]; then
|
|
log "Stage 6: Prepare BPE based lang"
|
|
|
|
for vocab_size in ${vocab_sizes[@]}; do
|
|
lang_dir=data/lang_bpe_${vocab_size}
|
|
mkdir -p $lang_dir
|
|
# We reuse words.txt from phone based lexicon
|
|
# so that the two can share G.pt later.
|
|
cp data/lang_phone/words.txt $lang_dir
|
|
|
|
if [ ! -f $lang_dir/transcript_words.txt ]; then
|
|
log "Generate data for BPE training"
|
|
cat data/lang_phone/train.text | cut -d " " -f 2-
|
|
> $lang_dir/transcript_words.txt
|
|
fi
|
|
|
|
./local/train_bpe_model.py \
|
|
--lang-dir $lang_dir \
|
|
--vocab-size $vocab_size \
|
|
--transcript $lang_dir/transcript_words.txt
|
|
|
|
if [ ! -f $lang_dir/L_disambig.pt ]; then
|
|
./local/prepare_lang_bpe.py --lang-dir $lang_dir
|
|
fi
|
|
done
|
|
fi
|
|
|
|
if [ $stage -le 7 ] && [ $stop_stage -ge 7 ]; then
|
|
log "Stage 7: Prepare bigram P"
|
|
|
|
for vocab_size in ${vocab_sizes[@]}; do
|
|
lang_dir=data/lang_bpe_${vocab_size}
|
|
|
|
if [ ! -f $lang_dir/transcript_tokens.txt ]; then
|
|
./local/convert_transcript_words_to_tokens.py \
|
|
--lexicon $lang_dir/lexicon.txt \
|
|
--transcript $lang_dir/transcript_words.txt \
|
|
--oov "<UNK>" \
|
|
> $lang_dir/transcript_tokens.txt
|
|
fi
|
|
|
|
if [ ! -f $lang_dir/P.arpa ]; then
|
|
./shared/make_kn_lm.py \
|
|
-ngram-order 2 \
|
|
-text $lang_dir/transcript_tokens.txt \
|
|
-lm $lang_dir/P.arpa
|
|
fi
|
|
|
|
if [ ! -f $lang_dir/P.fst.txt ]; then
|
|
python3 -m kaldilm \
|
|
--read-symbol-table="$lang_dir/tokens.txt" \
|
|
--disambig-symbol='#0' \
|
|
--max-order=2 \
|
|
$lang_dir/P.arpa > $lang_dir/P.fst.txt
|
|
fi
|
|
done
|
|
fi
|
|
|
|
if [ $stage -le 8 ] && [ $stop_stage -ge 8 ]; then
|
|
log "Stage 8: Prepare G"
|
|
# We assume you have install kaldilm, if not, please install
|
|
# it using: pip install kaldilm
|
|
|
|
mkdir -p data/lm
|
|
if [ ! -f data/lm/G_3_gram.fst.txt ]; then
|
|
# It is used in building HLG
|
|
python3 -m kaldilm \
|
|
--read-symbol-table="data/lang_phone/words.txt" \
|
|
--disambig-symbol='#0' \
|
|
--max-order=3 \
|
|
data/lm/lm_3_gram.arpa > data/lm/G_3_gram.fst.txt
|
|
fi
|
|
|
|
if [ ! -f data/lm/G_4_gram.fst.txt ]; then
|
|
# It is used for LM rescoring
|
|
python3 -m kaldilm \
|
|
--read-symbol-table="data/lang_phone/words.txt" \
|
|
--disambig-symbol='#0' \
|
|
--max-order=4 \
|
|
data/lm/lm_4_gram.arpa > data/lm/G_4_gram.fst.txt
|
|
fi
|
|
fi
|
|
echo 'completing the G building....'
|
|
if [ $stage -le 9 ] && [ $stop_stage -ge 9 ]; then
|
|
log "Stage 9: Compile HLG"
|
|
./local/compile_hlg.py --lang-dir data/lang_phone
|
|
|
|
for vocab_size in ${vocab_sizes[@]}; do
|
|
lang_dir=data/lang_bpe_${vocab_size}
|
|
./local/compile_hlg.py --lang-dir $lang_dir
|
|
done
|
|
fi
|