mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-08-14 12:32:20 +00:00
167 lines
4.7 KiB
Bash
Executable File
167 lines
4.7 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=3
|
|
stop_stage=3
|
|
|
|
# We assume dl_dir (download dir) contains the following
|
|
# directories and files. If not, they will be downloaded
|
|
# by this script automatically.
|
|
#
|
|
# - $dl_dir/icmcasr
|
|
# You can find data_icmcasr, resource_icmcasr inside it.
|
|
# You can download them from https://www.openslr.org/33
|
|
#
|
|
# - $dl_dir/musan
|
|
# This directory contains the following directories downloaded from
|
|
# http://www.openslr.org/17/
|
|
#
|
|
# - music
|
|
# - noise
|
|
# - speech
|
|
|
|
# ln -s /your/parent/path/to/ICMC-ASR $PWD/downloa
|
|
dl_dir=$PWD/download
|
|
|
|
. shared/parse_options.sh || exit 1
|
|
|
|
# vocab size for sentence piece models.
|
|
# It will generate data/lang_bbpe_xxx,
|
|
# data/lang_bbpe_yyy if the array contains xxx, yyy
|
|
vocab_sizes=(
|
|
# 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: Prepare icmcasr manifest"
|
|
# We assume that you have downloaded the icmcasr corpus
|
|
# to $dl_dir/icmcasr
|
|
if [ ! -f data/manifests/.icmcasr_manifests.done ]; then
|
|
mkdir -p data/manifests
|
|
for part in ihm sdm; do
|
|
lhotse prepare icmcasr --mic ${part} $dl_dir/ICMC-ASR data/manifests
|
|
done
|
|
touch data/manifests/.icmcasr_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
|
|
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 icmcasr"
|
|
if [ ! -f data/fbank/.icmcasr.done ]; then
|
|
mkdir -p data/fbank
|
|
./local/compute_fbank_icmcasr.py --perturb-speed True
|
|
touch data/fbank/.icmcasr.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
|
|
|
|
lang_phone_dir=data/lang_phone
|
|
if [ $stage -le 5 ] && [ $stop_stage -ge 5 ]; then
|
|
log "Stage 5: Prepare phone based lang"
|
|
mkdir -p $lang_phone_dir
|
|
|
|
(echo '!SIL SIL'; echo '<SPOKEN_NOISE> SPN'; echo '<UNK> SPN'; ) |
|
|
cat - $dl_dir/icmcasr/resource_icmcasr/lexicon.txt |
|
|
sort | uniq > $lang_phone_dir/lexicon.txt
|
|
|
|
./local/generate_unique_lexicon.py --lang-dir $lang_phone_dir
|
|
|
|
if [ ! -f $lang_phone_dir/L_disambig.pt ]; then
|
|
./local/prepare_lang.py --lang-dir $lang_phone_dir
|
|
fi
|
|
fi
|
|
|
|
lang_char_dir=data/lang_char
|
|
if [ $stage -le 6 ] && [ $stop_stage -ge 6 ]; then
|
|
log "Stage 6: Prepare char based lang"
|
|
mkdir -p $lang_char_dir
|
|
# We reuse words.txt from phone based lexicon
|
|
# so that the two can share G.pt later.
|
|
|
|
# The transcripts in training set, generated in stage 5
|
|
cp $lang_phone_dir/transcript_words.txt $lang_char_dir/transcript_words.txt
|
|
|
|
cat $dl_dir/icmcasr/data_icmcasr/transcript/icmcasr_transcript_v0.8.txt |
|
|
cut -d " " -f 2- > $lang_char_dir/text
|
|
|
|
(echo '<eps> 0'; echo '!SIL 1'; echo '<SPOKEN_NOISE> 2'; echo '<UNK> 3';) \
|
|
> $lang_char_dir/words.txt
|
|
|
|
cat $lang_char_dir/text | sed 's/ /\n/g' | sort -u | sed '/^$/d' \
|
|
| awk '{print $1" "NR+3}' >> $lang_char_dir/words.txt
|
|
|
|
num_lines=$(< $lang_char_dir/words.txt wc -l)
|
|
(echo "#0 $num_lines"; echo "<s> $(($num_lines + 1))"; echo "</s> $(($num_lines + 2))";) \
|
|
>> $lang_char_dir/words.txt
|
|
|
|
if [ ! -f $lang_char_dir/L_disambig.pt ]; then
|
|
./local/prepare_char.py --lang-dir $lang_char_dir
|
|
fi
|
|
|
|
if [ ! -f $lang_char_dir/HLG.fst ]; then
|
|
./local/prepare_lang_fst.py --lang-dir $lang_phone_dir --ngram-G ./data/lm/G_3_gram.fst.txt
|
|
fi
|
|
fi
|
|
|
|
if [ $stage -le 7 ] && [ $stop_stage -ge 7 ]; then
|
|
log "Stage 7: Prepare Byte BPE based lang"
|
|
|
|
for vocab_size in ${vocab_sizes[@]}; do
|
|
lang_dir=data/lang_bbpe_${vocab_size}
|
|
mkdir -p $lang_dir
|
|
|
|
cp $lang_char_dir/words.txt $lang_dir
|
|
cp $lang_char_dir/text $lang_dir
|
|
|
|
if [ ! -f $lang_dir/bbpe.model ]; then
|
|
./local/train_bbpe_model.py \
|
|
--lang-dir $lang_dir \
|
|
--vocab-size $vocab_size \
|
|
--transcript $lang_dir/text
|
|
fi
|
|
|
|
if [ ! -f $lang_dir/L_disambig.pt ]; then
|
|
./local/prepare_lang_bbpe.py --lang-dir $lang_dir
|
|
fi
|
|
done
|
|
fi
|