From 5dd5332fd50ed3f81ac34b375f71144f27fd2711 Mon Sep 17 00:00:00 2001
From: 嘉渊 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期四, 11 五月 2023 17:00:44 +0800
Subject: [PATCH] update repo
---
egs/aishell/transformer/run.sh | 69 +++++++++++++++-
/dev/null | 53 -------------
egs/aishell/transformer/local/download_and_untar.sh | 105 ++++++++++++++++++++++++++
3 files changed, 167 insertions(+), 60 deletions(-)
diff --git a/egs/aishell/transformer/local/download_and_untar.sh b/egs/aishell/transformer/local/download_and_untar.sh
new file mode 100755
index 0000000..d982559
--- /dev/null
+++ b/egs/aishell/transformer/local/download_and_untar.sh
@@ -0,0 +1,105 @@
+#!/usr/bin/env bash
+
+# Copyright 2014 Johns Hopkins University (author: Daniel Povey)
+# 2017 Xingyu Na
+# Apache 2.0
+
+remove_archive=false
+
+if [ "$1" == --remove-archive ]; then
+ remove_archive=true
+ shift
+fi
+
+if [ $# -ne 3 ]; then
+ echo "Usage: $0 [--remove-archive] <data-base> <url-base> <corpus-part>"
+ echo "e.g.: $0 /export/a05/xna/data www.openslr.org/resources/33 data_aishell"
+ echo "With --remove-archive it will remove the archive after successfully un-tarring it."
+ echo "<corpus-part> can be one of: data_aishell, resource_aishell."
+fi
+
+data=$1
+url=$2
+part=$3
+
+if [ ! -d "$data" ]; then
+ echo "$0: no such directory $data"
+ exit 1;
+fi
+
+part_ok=false
+list="data_aishell resource_aishell"
+for x in $list; do
+ if [ "$part" == $x ]; then part_ok=true; fi
+done
+if ! $part_ok; then
+ echo "$0: expected <corpus-part> to be one of $list, but got '$part'"
+ exit 1;
+fi
+
+if [ -z "$url" ]; then
+ echo "$0: empty URL base."
+ exit 1;
+fi
+
+if [ -f $data/$part/.complete ]; then
+ echo "$0: data part $part was already successfully extracted, nothing to do."
+ exit 0;
+fi
+
+# sizes of the archive files in bytes.
+sizes="15582913665 1246920"
+
+if [ -f $data/$part.tgz ]; then
+ size=$(/bin/ls -l $data/$part.tgz | awk '{print $5}')
+ size_ok=false
+ for s in $sizes; do if [ $s == $size ]; then size_ok=true; fi; done
+ if ! $size_ok; then
+ echo "$0: removing existing file $data/$part.tgz because its size in bytes $size"
+ echo "does not equal the size of one of the archives."
+ rm $data/$part.tgz
+ else
+ echo "$data/$part.tgz exists and appears to be complete."
+ fi
+fi
+
+if [ ! -f $data/$part.tgz ]; then
+ if ! command -v wget >/dev/null; then
+ echo "$0: wget is not installed."
+ exit 1;
+ fi
+ full_url=$url/$part.tgz
+ echo "$0: downloading data from $full_url. This may take some time, please be patient."
+
+ cd $data || exit 1
+ if ! wget --no-check-certificate $full_url; then
+ echo "$0: error executing wget $full_url"
+ exit 1;
+ fi
+fi
+
+cd $data || exit 1
+
+if ! tar -xvzf $part.tgz; then
+ echo "$0: error un-tarring archive $data/$part.tgz"
+ exit 1;
+fi
+
+touch $data/$part/.complete
+
+if [ $part == "data_aishell" ]; then
+ cd $data/$part/wav || exit 1
+ for wav in ./*.tar.gz; do
+ echo "Extracting wav from $wav"
+ tar -zxf $wav && rm $wav
+ done
+fi
+
+echo "$0: Successfully downloaded and un-tarred $data/$part.tgz"
+
+if $remove_archive; then
+ echo "$0: removing $data/$part.tgz file since --remove-archive option was supplied."
+ rm $data/$part.tgz
+fi
+
+exit 0;
diff --git a/egs/aishell/transformer/local/prepare_data.sh b/egs/aishell/transformer/local/prepare_data.sh
deleted file mode 100755
index 77791f9..0000000
--- a/egs/aishell/transformer/local/prepare_data.sh
+++ /dev/null
@@ -1,53 +0,0 @@
-#!/usr/bin/env bash
-# Copyright 2018 AIShell-Foundation(Authors:Jiayu DU, Xingyu NA, Bengu WU, Hao ZHENG)
-# 2018 Beijing Shell Shell Tech. Co. Ltd. (Author: Hui BU)
-# Apache 2.0
-
-# transform raw AISHELL-2 data to kaldi format
-
-. ./path.sh || exit 1;
-
-tmp=
-dir=
-
-if [ $# != 3 ]; then
- echo "Usage: $0 <corpus-data-dir> <tmp-dir> <output-dir>"
- echo " $0 /export/AISHELL-2/iOS/train data/local/train data/train"
- exit 1;
-fi
-
-corpus=$1
-tmp=$2
-dir=$3
-
-echo "prepare_data.sh: Preparing data in $corpus"
-
-mkdir -p $tmp
-mkdir -p $dir
-
-# corpus check
-if [ ! -d $corpus ] || [ ! -f $corpus/wav.scp ] || [ ! -f $corpus/trans.txt ]; then
- echo "Error: $0 requires wav.scp and trans.txt under $corpus directory."
- exit 1;
-fi
-
-# validate utt-key list, IC0803W0380 is a bad utterance
-awk '{print $1}' $corpus/wav.scp | grep -v 'IC0803W0380' > $tmp/wav_utt.list
-awk '{print $1}' $corpus/trans.txt > $tmp/trans_utt.list
-utils/filter_scp.pl -f 1 $tmp/wav_utt.list $tmp/trans_utt.list > $tmp/utt.list
-
-# wav.scp
-awk -F'\t' -v path_prefix=$corpus '{printf("%s\t%s/%s\n",$1,path_prefix,$2)}' $corpus/wav.scp > $tmp/tmp_wav.scp
-utils/filter_scp.pl -f 1 $tmp/utt.list $tmp/tmp_wav.scp | sort -k 1 | uniq > $tmp/wav.scp
-
-# text
-utils/filter_scp.pl -f 1 $tmp/utt.list $corpus/trans.txt | sort -k 1 | uniq > $tmp/text
-
-# copy prepared resources from tmp_dir to target dir
-mkdir -p $dir
-for f in wav.scp text; do
- cp $tmp/$f $dir/$f || exit 1;
-done
-
-echo "local/prepare_data.sh succeeded"
-exit 0;
diff --git a/egs/aishell/transformer/run.sh b/egs/aishell/transformer/run.sh
index 00035b5..76a7661 100755
--- a/egs/aishell/transformer/run.sh
+++ b/egs/aishell/transformer/run.sh
@@ -3,12 +3,12 @@
. ./path.sh || exit 1;
# machines configuration
-CUDA_VISIBLE_DEVICES="2,3"
+CUDA_VISIBLE_DEVICES="0,1"
gpu_num=2
count=1
gpu_inference=true # Whether to perform gpu decoding, set false for cpu decoding
# for gpu decoding, inference_nj=ngpu*njob; for cpu decoding, inference_nj=njob
-njob=1
+njob=5
train_cmd=utils/run.pl
infer_cmd=utils/run.pl
@@ -16,13 +16,11 @@
feats_dir="../DATA" #feature output dictionary
exp_dir="."
lang=zh
-dumpdir=dump/fbank
-feats_type=fbank
token_type=char
-scp=wav.scp
type=sound
+scp=wav.scp
stage=3
-stop_stage=3
+stop_stage=4
# feature configuration
feats_dim=80
@@ -48,7 +46,7 @@
test_sets="dev test"
asr_config=conf/train_asr_transformer.yaml
-model_dir="baseline_$(basename "${asr_config}" .yaml)_${feats_type}_${lang}_${token_type}_${tag}"
+model_dir="baseline_$(basename "${asr_config}" .yaml)_${lang}_${token_type}_${tag}"
inference_config=conf/decode_asr_transformer.yaml
inference_asr_model=valid.acc.ave_10best.pb
@@ -143,4 +141,61 @@
} &
done
wait
+fi
+
+# Testing Stage
+if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
+ echo "stage 4: Inference"
+ for dset in ${test_sets}; do
+ asr_exp=${exp_dir}/exp/${model_dir}
+ inference_tag="$(basename "${inference_config}" .yaml)"
+ _dir="${asr_exp}/${inference_tag}/${inference_asr_model}/${dset}"
+ _logdir="${_dir}/logdir"
+ if [ -d ${_dir} ]; then
+ echo "${_dir} is already exists. if you want to decode again, please delete this dir first."
+ exit 0
+ fi
+ mkdir -p "${_logdir}"
+ _data="${feats_dir}/data/${dset}"
+ key_file=${_data}/${scp}
+ num_scp_file="$(<${key_file} wc -l)"
+ _nj=$([ $inference_nj -le $num_scp_file ] && echo "$inference_nj" || echo "$num_scp_file")
+ split_scps=
+ for n in $(seq "${_nj}"); do
+ split_scps+=" ${_logdir}/keys.${n}.scp"
+ done
+ # shellcheck disable=SC2086
+ utils/split_scp.pl "${key_file}" ${split_scps}
+ _opts=
+ if [ -n "${inference_config}" ]; then
+ _opts+="--config ${inference_config} "
+ fi
+ ${infer_cmd} --gpu "${_ngpu}" --max-jobs-run "${_nj}" JOB=1:"${_nj}" "${_logdir}"/asr_inference.JOB.log \
+ python -m funasr.bin.asr_inference_launch \
+ --batch_size 1 \
+ --ngpu "${_ngpu}" \
+ --njob ${njob} \
+ --gpuid_list ${gpuid_list} \
+ --data_path_and_name_and_type "${_data}/${scp},speech,${type}" \
+ --cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
+ --key_file "${_logdir}"/keys.JOB.scp \
+ --asr_train_config "${asr_exp}"/config.yaml \
+ --asr_model_file "${asr_exp}"/"${inference_asr_model}" \
+ --output_dir "${_logdir}"/output.JOB \
+ --mode asr \
+ ${_opts}
+
+ for f in token token_int score text; do
+ if [ -f "${_logdir}/output.1/1best_recog/${f}" ]; then
+ for i in $(seq "${_nj}"); do
+ cat "${_logdir}/output.${i}/1best_recog/${f}"
+ done | sort -k1 >"${_dir}/${f}"
+ fi
+ done
+ python utils/proce_text.py ${_dir}/text ${_dir}/text.proc
+ python utils/proce_text.py ${_data}/text ${_data}/text.proc
+ python utils/compute_wer.py ${_data}/text.proc ${_dir}/text.proc ${_dir}/text.cer
+ tail -n 3 ${_dir}/text.cer > ${_dir}/text.cer.txt
+ cat ${_dir}/text.cer.txt
+ done
fi
\ No newline at end of file
--
Gitblit v1.9.1