mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-08-09 10:02:22 +00:00
30c43b7f69
* Add aishell recipe * Remove unnecessary code and update docs * adapt to k2 v1.7, add docs and results * Update conformer ctc model * Update docs, pretrained.py & results * Fix code style * Fix code style * Fix code style * Minor fix * Minor fix * Fix pretrained.py * Update pretrained model & corresponding docs
163 lines
4.4 KiB
Bash
Executable File
163 lines
4.4 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
|
|
set -eou pipefail
|
|
|
|
nj=15
|
|
stage=-1
|
|
stop_stage=10
|
|
|
|
# We assume dl_dir (download dir) contains the following
|
|
# directories and files. If not, they will be downloaded
|
|
# by this script automatically.
|
|
#
|
|
# - $dl_dir/aishell
|
|
# You can find data_aishell, resource_aishell inside it.
|
|
# You can download them from https://www.openslr.org/33
|
|
#
|
|
# - $dl_dir/lm
|
|
# This directory contains the language model downloaded from
|
|
# https://huggingface.co/pkufool/aishell_lm
|
|
#
|
|
# - 3-gram.unpruned.apra
|
|
#
|
|
# - $dl_dir/musan
|
|
# This directory contains the following directories downloaded from
|
|
# http://www.openslr.org/17/
|
|
#
|
|
# - music
|
|
# - noise
|
|
# - speech
|
|
|
|
dl_dir=$PWD/download
|
|
|
|
. shared/parse_options.sh || exit 1
|
|
|
|
# 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: Download LM"
|
|
# We assume that you have installed the git-lfs, if not, you could install it
|
|
# using: `sudo apt-get install git-lfs && git-lfs install`
|
|
[ ! -e $dl_dir/lm ] && mkdir -p $dl_dir/lm
|
|
git clone https://huggingface.co/pkufool/aishell_lm $dl_dir/lm
|
|
fi
|
|
|
|
if [ $stage -le 0 ] && [ $stop_stage -ge 0 ]; then
|
|
log "stage 0: Download data"
|
|
|
|
# If you have pre-downloaded it to /path/to/aishell,
|
|
# you can create a symlink
|
|
#
|
|
# ln -sfv /path/to/aishell $dl_dir/aishell
|
|
#
|
|
# The directory structure is
|
|
# aishell/
|
|
# |-- data_aishell
|
|
# | |-- transcript
|
|
# | `-- wav
|
|
# `-- resource_aishell
|
|
# |-- lexicon.txt
|
|
# `-- speaker.info
|
|
|
|
if [ ! -d $dl_dir/aishell/data_aishell/wav ]; then
|
|
lhotse download aishell $dl_dir
|
|
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 aishell manifest"
|
|
# We assume that you have downloaded the aishell corpus
|
|
# to $dl_dir/aishell
|
|
mkdir -p data/manifests
|
|
lhotse prepare aishell -j $nj $dl_dir/aishell data/manifests
|
|
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
|
|
lhotse prepare musan $dl_dir/musan data/manifests
|
|
fi
|
|
|
|
if [ $stage -le 3 ] && [ $stop_stage -ge 3 ]; then
|
|
log "Stage 3: Compute fbank for aishell"
|
|
mkdir -p data/fbank
|
|
./local/compute_fbank_aishell.py
|
|
fi
|
|
|
|
if [ $stage -le 4 ] && [ $stop_stage -ge 4 ]; then
|
|
log "Stage 4: Compute fbank for musan"
|
|
mkdir -p data/fbank
|
|
./local/compute_fbank_musan.py
|
|
fi
|
|
|
|
if [ $stage -le 5 ] && [ $stop_stage -ge 5 ]; then
|
|
log "Stage 5: Prepare phone based lang"
|
|
mkdir -p data/lang_phone
|
|
|
|
(echo '!SIL SIL'; echo '<SPOKEN_NOISE> SPN'; echo '<UNK> SPN'; ) |
|
|
cat - $dl_dir/aishell/resource_aishell/lexicon.txt |
|
|
sort | uniq > data/lang_phone/lexicon.txt
|
|
|
|
if [ ! -f data/lang_phone/L_disambig.pt ]; then
|
|
./local/prepare_lang.py
|
|
fi
|
|
fi
|
|
|
|
if [ $stage -le 6 ] && [ $stop_stage -ge 6 ]; then
|
|
log "Stage 6: Prepare char based lang"
|
|
mkdir -p data/lang_char
|
|
# We reuse words.txt from phone based lexicon
|
|
# so that the two can share G.pt later.
|
|
cp data/lang_phone/words.txt data/lang_char
|
|
|
|
cat $dl_dir/aishell/data_aishell/transcript/aishell_transcript_v0.8.txt |
|
|
cut -d " " -f 2- | sed -e 's/[ \t\r\n]*//g' > data/lang_char/text
|
|
|
|
if [ ! -f data/lang_char/L_disambig.pt ]; then
|
|
./local/prepare_char.py
|
|
fi
|
|
fi
|
|
|
|
if [ $stage -le 7 ] && [ $stop_stage -ge 7 ]; then
|
|
log "Stage 7: 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.unpruned.arpa > data/lm/G_3_gram.fst.txt
|
|
fi
|
|
fi
|
|
|
|
if [ $stage -le 8 ] && [ $stop_stage -ge 8 ]; then
|
|
log "Stage 8: Compile HLG"
|
|
./local/compile_hlg.py --lang-dir data/lang_phone
|
|
./local/compile_hlg.py --lang-dir data/lang_char
|
|
fi
|