icefall/egs/tal_csasr/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

set -eou pipefail

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/TALCS_corpus
#      You can find three directories:train_set, dev_set, and test_set.
#      You can get it from https://ai.100tal.com/dataset
#     - dev_set
#     - test_set
#     - train_set
#
#  - $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_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 0 ] && [ $stop_stage -ge 0 ]; then
  log "Stage 0: Download data"
  # Before you run this script, you must get the TAL_CSASR dataset
  # from https://ai.100tal.com/dataset
  if [ ! -d $dl_dir/tal_csasr/TALCS_corpus ]; then
    mv $dl_dir/TALCS_corpus $dl_dir/tal_csasr
  fi

  # If you have pre-downloaded it to /path/to/TALCS_corpus,
  # you can create a symlink
  #
  #   ln -sfv /path/to/TALCS_corpus $dl_dir/tal_csasr

  # 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 tal_csasr manifest"
  # We assume that you have downloaded the TALCS_corpus
  # to $dl_dir/tal_csasr
  if [ ! -f data/manifests/tal_csasr/.manifests.done ]; then
    mkdir -p data/manifests/tal_csasr
    lhotse prepare tal-csasr $dl_dir/tal_csasr data/manifests/tal_csasr
    touch data/manifests/tal_csasr/.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 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 4 ] && [ $stop_stage -ge 4 ]; then
  log "Stage 4: Compute fbank for tal_csasr"
  if [ ! -f data/fbank/.tal_csasr.done ]; then
    mkdir -p data/fbank
    ./local/compute_fbank_tal_csasr.py
    touch data/fbank/.tal_csasr.done
  fi
fi

if [ $stage -le 5 ] && [ $stop_stage -ge 5 ]; then
  log "Stage 5: Prepare char based lang"
  lang_char_dir=data/lang_char
  mkdir -p $lang_char_dir

  # Download BPE models trained with LibriSpeech
  # Here we use the BPE model with 5000 units trained with Librispeech.
  # You can also use other BPE models if available.
  if [ ! -f $lang_char_dir/bpe.model ]; then
    wget -O $lang_char_dir/bpe.model \
      https://huggingface.co/luomingshuang/bpe_models_trained_with_Librispeech/resolve/main/lang_bpe_500/bpe.model
  fi

  # we extract text from manifests rather than the label.txt in corpus, because
  # the texts in manifests have been normalized in lhotse.
  if [ ! -f $lang_char_dir/text ]; then
    gunzip -c data/manifests/tal_csasr/tal_csasr_supervisions_train_set.jsonl.gz \
      | grep -o 'text":\s[^,]*' | sed 's/text": "//g;s/"//g' \
      | ./local/text2token.py -t "char" > $lang_char_dir/text_train

    gunzip -c data/manifests/tal_csasr/tal_csasr_supervisions_dev_set.jsonl.gz \
      | grep -o 'text":\s[^,]*' | sed 's/text": "//g;s/"//g' \
      | ./local/text2token.py -t "char" > $lang_char_dir/text_dev

    gunzip -c data/manifests/tal_csasr/tal_csasr_supervisions_test_set.jsonl.gz \
      | grep -o 'text":\s[^,]*' | sed 's/text": "//g;s/"//g' \
      | ./local/text2token.py -t "char" > $lang_char_dir/text_test

    for r in text_train text_dev text_test ; do
      cat $lang_char_dir/$r >> $lang_char_dir/text
    done
  fi

  # Prepare words.txt
  # We assume you have installed jieba, if not, please install
  # it using: pip install jieba
  if [ ! -f $lang_char_dir/words.txt ]; then
    python -m jieba $lang_char_dir/text | sed 's/\///g;s/\s\+/ /g' > $lang_char_dir/text.seg

   (echo '<eps> 0'; echo '!SIL 1'; echo '<SPOKEN_NOISE> 2'; echo '<UNK> 3';) \
     > $lang_char_dir/words.txt

   cat $lang_char_dir/text.seg | sed 's/ /\n/g' | sort -u | sed '/^$/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
  fi

  # Tokenize text with BPE model
  python ./local/tokenize_with_bpe_model.py \
    --input $lang_char_dir/text \
    --output $lang_char_dir/text_with_bpe \
    --bpe-model $lang_char_dir/bpe.model

  if [ ! -f $lang_char_dir/L_disambig.pt ]; then
    python local/prepare_char.py
  fi
fi

if [ $stage -le 6 ] && [ $stop_stage -ge 6 ]; 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
    # We reuse words.txt from phone based lexicon
    # so that the two can share G.pt later.
    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
  done
fi