mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-08-09 18:12:19 +00:00
127 lines
3.7 KiB
Bash
Executable File
127 lines
3.7 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
|
|
stage=-1
|
|
stop_stage=100
|
|
|
|
dl_dir=$PWD/download
|
|
# The following files will be downloaded to $dl_dir
|
|
# - ptb.train.txt
|
|
# - ptb.valid.txt
|
|
# - ptb.test.txt
|
|
|
|
. shared/parse_options.sh || exit 1
|
|
|
|
# vocab size for sentence piece models.
|
|
# It will generate data/bpe_xxx, data/bpe_yyy
|
|
# if the array contains xxx, yyy
|
|
vocab_sizes=(
|
|
500
|
|
# 1000
|
|
# 2000
|
|
# 5000
|
|
)
|
|
|
|
# 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
|
|
mkdir -p $dl_dir
|
|
|
|
log() {
|
|
# This function is from espnet
|
|
local fname=${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 data"
|
|
|
|
# Caution: The downloaded data has already been normalized for LM training.
|
|
|
|
if [ ! -f $dl_dir/.complete ]; then
|
|
url=http://raw.githubusercontent.com/townie/PTB-dataset-from-Tomas-Mikolov-s-webpage/master/data
|
|
wget --directory-prefix $dl_dir $url/ptb.train.txt
|
|
wget --directory-prefix $dl_dir $url/ptb.valid.txt
|
|
wget --directory-prefix $dl_dir $url/ptb.test.txt
|
|
touch $dl_dir/.complete
|
|
fi
|
|
fi
|
|
|
|
if [ $stage -le 0 ] && [ $stop_stage -ge 0 ]; then
|
|
log "Stage 0: Train BPE model"
|
|
|
|
# Caution: You have to use the same bpe model for training your acoustic model
|
|
# Caution: You have to use the same bpe model for training your acoustic model
|
|
# Caution: You have to use the same bpe model for training your acoustic model
|
|
|
|
for vocab_size in ${vocab_sizes[@]}; do
|
|
lang_dir=data/lang_bpe_${vocab_size}
|
|
mkdir -p $lang_dir
|
|
./local/train_bpe_model.py \
|
|
--lang-dir $lang_dir \
|
|
--vocab-size $vocab_size \
|
|
--transcript $dl_dir/ptb.train.txt
|
|
done
|
|
fi
|
|
|
|
if [ $stage -le 1 ] && [ $stop_stage -ge 1 ]; then
|
|
log "Stage 1: Generate LM training data"
|
|
# Note: ptb.train.txt has already been normalized
|
|
|
|
for vocab_size in ${vocab_sizes[@]}; do
|
|
lang_dir=data/lang_bpe_${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/ptb.train.txt \
|
|
--lm-archive $out_dir/lm_data.pt
|
|
|
|
./local/prepare_lm_training_data.py \
|
|
--bpe-model $lang_dir/bpe.model \
|
|
--lm-data $dl_dir/ptb.valid.txt \
|
|
--lm-archive $out_dir/lm_data-valid.pt
|
|
|
|
./local/prepare_lm_training_data.py \
|
|
--bpe-model $lang_dir/bpe.model \
|
|
--lm-data $dl_dir/ptb.test.txt \
|
|
--lm-archive $out_dir/lm_data-test.pt
|
|
done
|
|
fi
|
|
|
|
if [ $stage -le 2 ] && [ $stop_stage -ge 2 ]; then
|
|
log "Stage 2: Sort LM training data"
|
|
# Sort LM training data generated in stage 1
|
|
# 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
|