From fb65bb99162c79e46dbade0e80765cf20ca436cc Mon Sep 17 00:00:00 2001 From: dohe0342 Date: Tue, 21 Feb 2023 14:31:28 +0900 Subject: [PATCH] from local --- egs/tedlium2/ASR/prepare_ted3.sh | 239 +++++++++++++++++++++++++++++++ 1 file changed, 239 insertions(+) create mode 100755 egs/tedlium2/ASR/prepare_ted3.sh diff --git a/egs/tedlium2/ASR/prepare_ted3.sh b/egs/tedlium2/ASR/prepare_ted3.sh new file mode 100755 index 000000000..31e0ac32e --- /dev/null +++ b/egs/tedlium2/ASR/prepare_ted3.sh @@ -0,0 +1,239 @@ +#!/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=0 +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/tedlium2 +# You can find data, doc, legacy, LM, etc, inside it. +# You can download them from https://www.openslr.org/51 +# +# - $dl_dir/musan +# This directory contains the following directories downloaded from +# http://www.openslr.org/17/ +# +# - music +# - noise +# - speech +dl_dir=/DB/LibriSpeech_tar + +. shared/parse_options.sh || exit 1 + +# vocab size for sentence piece models. +# It will generate data/lang_bpe_xxx, +# data/lang_bpe_yyy if the array contains xxx, yyy +vocab_sizes=( + 5000 + 2000 + 1000 + 500 +) + +# All files generated by this script are saved in "data". +# You can safely remove "data" and rerun this script to regenerate it. +mkdir -p data + +log() { + # This function is from espnet + local fname=${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 0 ] && [ $stop_stage -ge 0 ]; then + log "Stage 0: Download data" + + # If you have pre-downloaded it to /path/to/tedlium3, + # you can create a symlink + # + # ln -sfv /path/to/tedlium3 $dl_dir/tedlium3 + # + #if [ ! -d $dl_dir/tedlium2 ]; then + # lhotse download tedlium $dl_dir + # mv $dl_dir/TEDLIUM_release-2 $dl_dir/tedlium2 + #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 tedlium2 manifests" + if [ ! -f data/manifests/.tedlium2.done ]; then + # We assume that you have downloaded the tedlium3 corpus + # to $dl_dir/tedlium3 + mkdir -p data/manifests + lhotse prepare tedlium $dl_dir/tedlium2 data/manifests + touch data/manifests/.tedlium2.done + fi +fi + +if [ $stage -le 2 ] && [ $stop_stage -ge 2 ]; then + log "Stage 2: Prepare musan manifests" + # We assume that you have downloaded the musan corpus + # to data/musan + if [ ! -e data/manifests/.musan.done ]; then + mkdir -p data/manifests + 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: Compute fbank for tedlium2" + + if [ ! -e data/fbank/.tedlium2.done ]; then + mkdir -p data/fbank + python3 ./local/compute_fbank_tedlium.py + touch data/fbank/.tedlium2.done + fi +fi + +if [ $stage -le 4 ] && [ $stop_stage -ge 4 ]; then + log "Stage 4: Compute fbank for musan" + if [ ! -e data/fbank/.musan.done ]; then + mkdir -p data/fbank + python3 ./local/compute_fbank_musan.py + touch data/fbank/.musan.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 + + if [ ! -f $lang_dir/train.text ]; then + ./local/prepare_transcripts.py \ + --lang-dir $lang_dir \ + --manifests-dir data/manifests + fi + + if [ ! -f $lang_dir/lexicon_words.txt ]; then + ./local/prepare_lexicon.py \ + --lang-dir $lang_dir \ + --manifests-dir data/manifests + fi + + (echo '!SIL SIL'; echo ' '; ) | + 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 + # remove the for transcript_words.txt + sed -i 's/ //g' $lang_dir/transcript_words.txt + sed -i 's/ //g' $lang_dir/transcript_words.txt + sed -i 's///g' $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 "" \ + > $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 \ + $dl_dir/lm/3-gram.pruned.1e-7.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/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 +