mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-08-08 09:32:20 +00:00
358 lines
10 KiB
Bash
Executable File
358 lines
10 KiB
Bash
Executable File
#!/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/xbmu_amdo31
|
|
# You can find data, resource, etc, inside it.
|
|
# You can download them from https://huggingface.co/datasets/syzym/xbmu_amdo31
|
|
#
|
|
# - $dl_dir/lm
|
|
# This directory contains the following files downloaded from
|
|
# git lfs install
|
|
# https://huggingface.co/syzym/xbmu_amdo31_lm
|
|
#
|
|
# - tibetan.3-gram.arpa
|
|
# - tibetan.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=(
|
|
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"
|
|
# We assume that you have installed the git-lfs, if not, you could install it
|
|
# using: `sudo apt-get install git-lfs && git-lfs install`
|
|
git lfs 1>/dev/null 2>&1 || (echo "please install git-lfs, consider using: sudo apt-get install git-lfs && git-lfs install" && exit 1)
|
|
|
|
if [ ! -f $dl_dir/lm/3-gram.unpruned.arpa ]; then
|
|
git clone https://huggingface.co/syzym/xbmu_amdo31_lm $dl_dir/lm
|
|
pushd $dl_dir/lm
|
|
git lfs pull --include "tibetan.3-gram.arpa"
|
|
git lfs pull --include "tibetan.4-gram.arpa"
|
|
popd
|
|
fi
|
|
fi
|
|
|
|
if [ $stage -le 0 ] && [ $stop_stage -ge 0 ]; then
|
|
log "Stage 0: Download data"
|
|
|
|
# If you have pre-downloaded it to /path/to/xbmu_amdo31,
|
|
# you can create a symlink
|
|
#
|
|
# ln -sfv /path/to/xbmu_amdo31 $dl_dir/xbmu_amdo31
|
|
#
|
|
|
|
if [ ! -f $dl_dir/xbmu_amdo31 ]; then
|
|
git lfs 1>/dev/null 2>&1 || (echo "please install git-lfs, consider using: sudo apt-get install git-lfs && git-lfs install" && exit 1)
|
|
lhotse download xbmu-amdo31 $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 xbmu_amdo31 manifest"
|
|
# We assume that you have downloaded the xbmu_amdo31 corpus
|
|
# to $dl_dir/xbmu_amdo31
|
|
if [ ! -f data/manifests/.xbmu_amdo31_manifests.done ]; then
|
|
mkdir -p data/manifests
|
|
lhotse prepare xbmu-amdo31 $dl_dir/xbmu_amdo31 data/manifests
|
|
touch data/manifests/.xbmu_amdo31_manifests.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
|
|
if [ ! -f data/manifests/.musan_manifests.done ]; then
|
|
log "It may take 6 minutes"
|
|
mkdir -p data/manifests
|
|
lhotse prepare musan $dl_dir/musan data/manifests
|
|
touch data/manifests/.musan_manifests.done
|
|
fi
|
|
fi
|
|
|
|
if [ $stage -le 3 ] && [ $stop_stage -ge 3 ]; then
|
|
log "Stage 3: Compute fbank for xbmu_amdo31"
|
|
if [ ! -f data/fbank/.xbmu_amdo31.done ]; then
|
|
mkdir -p data/fbank
|
|
./local/compute_fbank_xbmu_amdo31.py
|
|
touch data/fbank/.xbmu_amdo31.done
|
|
fi
|
|
fi
|
|
|
|
|
|
|
|
if [ $stage -le 4 ] && [ $stop_stage -ge 4 ]; then
|
|
log "Stage 4: Compute fbank for musan"
|
|
if [ ! -f data/fbank/.msuan.done ]; then
|
|
mkdir -p data/fbank
|
|
./local/compute_fbank_musan.py
|
|
touch data/fbank/.msuan.done
|
|
fi
|
|
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
|
|
|
|
(echo '!SIL SIL'; echo '<SPOKEN_NOISE> SPN'; echo '<UNK> SPN'; ) |
|
|
cat - $dl_dir/xbmu_amdo31/resource/lexicon.txt |
|
|
sort | uniq > $lang_dir/lexicon.txt
|
|
|
|
./local/generate_unique_lexicon.py --lang-dir $lang_dir
|
|
|
|
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 $lang_dir/transcript_words.txt ]; then
|
|
log "Generate data to train phone based bigram P"
|
|
xbmu_amdo31_text=$dl_dir/xbmu_amdo31/data/transcript/transcript_clean.txt
|
|
xbmu_amdo31_train_uid=$dl_dir/xbmu_amdo31/data/transcript/xbmu_amdo31_train_uid
|
|
find $dl_dir/xbmu_amdo31/data/wav/train -name "*.wav" | sed 's/\.wav//g' | awk -F '-' '{print $NF}' > $xbmu_amdo31_train_uid
|
|
awk 'NR==FNR{uid[$1]=$1} NR!=FNR{if($1 in uid) print $0}' $xbmu_amdo31_train_uid $xbmu_amdo31_text |
|
|
cut -d " " -f 2- > $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 \
|
|
--transcript $lang_dir/transcript_words.txt
|
|
fi
|
|
|
|
if [ ! -f $lang_dir/L_disambig.pt ]; then
|
|
./local/prepare_lang_bpe.py --lang-dir $lang_dir
|
|
|
|
log "Validating $lang_dir/lexicon.txt"
|
|
./local/validate_bpe_lexicon.py \
|
|
--lexicon $lang_dir/lexicon.txt \
|
|
--bpe-model $lang_dir/bpe.model
|
|
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 installed 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 \
|
|
$dl_dir/lm/tibetan.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 \
|
|
$dl_dir/lm/tibetan.4-gram.arpa > data/lm/G_4_gram.fst.txt
|
|
fi
|
|
fi
|
|
|
|
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
|
|
|
|
# Compile LG for RNN-T fast_beam_search decoding
|
|
if [ $stage -le 10 ] && [ $stop_stage -ge 10 ]; then
|
|
log "Stage 10: Compile LG"
|
|
./local/compile_lg.py --lang-dir data/lang_phone
|
|
|
|
for vocab_size in ${vocab_sizes[@]}; do
|
|
lang_dir=data/lang_bpe_${vocab_size}
|
|
./local/compile_lg.py --lang-dir $lang_dir
|
|
done
|
|
fi
|
|
|
|
if [ $stage -le 11 ] && [ $stop_stage -ge 11 ]; then
|
|
log "Stage 11: Generate LM training data"
|
|
|
|
for vocab_size in ${vocab_sizes[@]}; do
|
|
log "Processing vocab_size == ${vocab_size}"
|
|
lang_dir=data/lang_bpe_${vocab_size}
|
|
out_dir=data/lm_training_bpe_${vocab_size}
|
|
mkdir -p $out_dir
|
|
|
|
./local/prepare_lm_training_data.py \
|
|
--bpe-model $lang_dir/bpe.model \
|
|
--lm-data $dl_dir/lm/lm_train.txt \
|
|
--lm-archive $out_dir/lm_data.pt
|
|
done
|
|
fi
|
|
|
|
if [ $stage -le 12 ] && [ $stop_stage -ge 12 ]; then
|
|
log "Stage 12: Generate LM validation data"
|
|
|
|
for vocab_size in ${vocab_sizes[@]}; do
|
|
log "Processing vocab_size == ${vocab_size}"
|
|
out_dir=data/lm_training_bpe_${vocab_size}
|
|
mkdir -p $out_dir
|
|
|
|
if [ ! -f $out_dir/valid.txt ]; then
|
|
files=$dl_dir/xbmu_amdo31/data/transcript/dev_text
|
|
for f in ${files[@]}; do
|
|
cat $f | cut -d " " -f 2-
|
|
done > $out_dir/valid.txt
|
|
fi
|
|
|
|
lang_dir=data/lang_bpe_${vocab_size}
|
|
./local/prepare_lm_training_data.py \
|
|
--bpe-model $lang_dir/bpe.model \
|
|
--lm-data $out_dir/valid.txt \
|
|
--lm-archive $out_dir/lm_data-valid.pt
|
|
done
|
|
fi
|
|
|
|
if [ $stage -le 13 ] && [ $stop_stage -ge 13 ]; then
|
|
log "Stage 13: Generate LM test data"
|
|
|
|
for vocab_size in ${vocab_sizes[@]}; do
|
|
log "Processing vocab_size == ${vocab_size}"
|
|
out_dir=data/lm_training_bpe_${vocab_size}
|
|
mkdir -p $out_dir
|
|
|
|
if [ ! -f $out_dir/test.txt ]; then
|
|
files=$dl_dir/xbmu_amdo31/data/transcript/test_text
|
|
cat $f | cut -d " " -f 2- > $out_dir/test.txt
|
|
fi
|
|
|
|
lang_dir=data/lang_bpe_${vocab_size}
|
|
./local/prepare_lm_training_data.py \
|
|
--bpe-model $lang_dir/bpe.model \
|
|
--lm-data $out_dir/test.txt \
|
|
--lm-archive $out_dir/lm_data-test.pt
|
|
done
|
|
fi
|
|
|
|
if [ $stage -le 14 ] && [ $stop_stage -ge 14 ]; then
|
|
log "Stage 14: Sort LM training data"
|
|
# Sort LM training data by sentence length in descending order
|
|
# for ease of training.
|
|
#
|
|
# Sentence length equals to the number of BPE tokens
|
|
# in a sentence.
|
|
|
|
for vocab_size in ${vocab_sizes[@]}; do
|
|
out_dir=data/lm_training_bpe_${vocab_size}
|
|
mkdir -p $out_dir
|
|
./local/sort_lm_training_data.py \
|
|
--in-lm-data $out_dir/lm_data.pt \
|
|
--out-lm-data $out_dir/sorted_lm_data.pt \
|
|
--out-statistics $out_dir/statistics.txt
|
|
|
|
./local/sort_lm_training_data.py \
|
|
--in-lm-data $out_dir/lm_data-valid.pt \
|
|
--out-lm-data $out_dir/sorted_lm_data-valid.pt \
|
|
--out-statistics $out_dir/statistics-valid.txt
|
|
|
|
./local/sort_lm_training_data.py \
|
|
--in-lm-data $out_dir/lm_data-test.pt \
|
|
--out-lm-data $out_dir/sorted_lm_data-test.pt \
|
|
--out-statistics $out_dir/statistics-test.txt
|
|
done
|
|
fi
|