icefall/egs/LJSpeech/ASR/prepare.sh

#!/usr/bin/env bash

# fix segmentation fault reported in https://github.com/k2-fsa/icefall/issues/674
export PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION=python
#. ../../../tools/activate_python.sh

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/LJSpeech
#      You can find BOOKS.TXT, test-clean, train-clean-360, etc, inside it.
#      You can download them from https://www.openslr.org/12
#
#  - $dl_dir/lm
#      This directory contains the following files downloaded from
#       http://www.openslr.org/resources/11
#
#        - 3-gram.pruned.1e-7.arpa.gz
#        - 3-gram.pruned.1e-7.arpa
#        - 4-gram.arpa.gz
#        - 4-gram.arpa
#        - LJSpeech-vocab.txt
#        - LJSpeech-lexicon.txt
#        - LJSpeech-lm-norm.txt.gz
#
#  - $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/LJSpeech,
  # you can create a symlink
  #
  #   ln -sfv /path/to/LJSpeech $dl_dir/LJSpeech
  #
  if [ ! -d $dl_dir/LJSpeech/wav ]; then
    echo "download not supported yet";
  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 LJSpeech manifest"
  # We assume that you have downloaded the LJSpeech corpus (ver 1.1)
  # You need to prepare LJSpeech according to data_settings/*_list.txt like below
  # $dl_dir/LJSpeech
  # |-- wavs
  # |   |-- train
  # |   |-- dev
  # |   |-- test
  # |-- texts
  # |-- metadata.csv

  # to $dl_dir/LJSpeech
  if [ ! -e $dl_dir/LJSpeech/.LJSpeech.done ]; then
    for dset in "train" "dev" "test"; do
      log "Resampling LJSpeech $dset set"
      file_list=`ls $dl_dir/LJSpeech/wavs/$dset/`
      for wavfile in $file_list; do
        sox -v 0.9 $dl_dir/LJSpeech/wavs/$dset/$wavfile -r 16000 -e signed-integer $dl_dir/LJSpeech/wavs/$dset/tmp_$wavfile
        mv $dl_dir/LJSpeech/wavs/$dset/tmp_$wavfile $dl_dir/LJSpeech/wavs/$dset/$wavfile
      done
      log "Resampling $dset done"
    done
    python local/prepare_LJSpeech_text.py $dl_dir/LJSpeech/metadata.csv
    touch $dl_dir/LJSpeech/.LJSpeech.done
  fi

  mkdir -p data/manifests
  if [ ! -e data/manifests/.LJSpeech.done ]; then
    python local/prepare_LJSpeech.py $dl_dir/LJSpeech
    touch data/manifests/.LJSpeech.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
  mkdir -p data/manifests
  if [ ! -e data/manifests/.musan.done ]; then
    lhotse prepare musan $dl_dir/musan data/manifests
    touch data/manifests/.musan.done
  fi
fi

if [ $stage -le 2 ] && [ $stop_stage -ge 2 ]; then
  log "Stage 3: Compute fbank for LJSpeech"
  mkdir -p data/fbank
  if [ ! -e data/fbank/.LJSpeech.done ]; then
    ./local/compute_fbank_LJSpeech.py --data-dir $dl_dir/LJSpeech
    touch data/fbank/.LJSpeech.done
  fi

  if [ ! -e data/fbank/.LJSpeech-validated.done ]; then
    log "Validating data/fbank for LJSpeech"
    parts=`ls $dl_dir/LJSpeech/wavs/`
    for part in ${parts[@]}; do
      python3 ./local/validate_manifest.py \
        data/fbank/LJSpeech_cuts_${part}.jsonl.gz
    done
  fi
fi

if [ $stage -le 4 ] && [ $stop_stage -ge 4 ]; then
  log "Stage 4: Compute fbank for musan"
  mkdir -p data/fbank
  if [ ! -e data/fbank/.musan.done ]; then
    ./local/compute_fbank_musan.py
    touch data/fbank/.musan.done
  fi
fi