update repo

egs/aishell/conformer/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;

egs/aishell/conformer/local/prepare_data.sh

@@ -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;

egs/aishell/conformer/run.sh

@@ -8,7 +8,7 @@ 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
 
@@ -16,10 +16,9 @@ infer_cmd=utils/run.pl
 feats_dir="../DATA" #feature output dictionary
 exp_dir="."
 lang=zh
-feats_type=fbank
 token_type=char
-scp=wav.scp
 type=sound
+scp=wav.scp
 stage=3
 stop_stage=4
 
@@ -47,7 +46,7 @@ valid_set=dev
 test_sets="dev test"
 
 asr_config=conf/train_asr_conformer.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

egs/librispeech_100h/conformer/local/download_and_untar.sh

@@ -0,0 +1,97 @@
+#!/usr/bin/env bash
+
+# Copyright   2014  Johns Hopkins University (author: Daniel Povey)
+# 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/a15/vpanayotov/data www.openslr.org/resources/11 dev-clean"
+  echo "With --remove-archive it will remove the archive after successfully un-tarring it."
+  echo "<corpus-part> can be one of: dev-clean, test-clean, dev-other, test-other,"
+  echo "          train-clean-100, train-clean-360, train-other-500."
+  exit 1
+fi
+
+data=$1
+url=$2
+part=$3
+
+if [ ! -d "$data" ]; then
+  echo "$0: no such directory $data"
+  exit 1
+fi
+
+part_ok=false
+list="dev-clean test-clean dev-other test-other train-clean-100 train-clean-360 train-other-500"
+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 $data/LibriSpeech/$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.  This is some older versions.
+sizes_old="371012589 347390293 379743611 361838298 6420417880 23082659865 30626749128"
+# sizes_new is the archive file sizes of the final release.  Some of these sizes are of
+# things we probably won't download.
+sizes_new="337926286 314305928 695964615 297279345 87960560420 33373768 346663984 328757843 6387309499 23049477885 30593501606"
+
+if [ -f $data/$part.tar.gz ]; then
+  size=$(/bin/ls -l $data/$part.tar.gz | awk '{print $5}')
+  size_ok=false
+  for s in $sizes_old $sizes_new; do if [ $s == $size ]; then size_ok=true; fi; done
+  if ! $size_ok; then
+    echo "$0: removing existing file $data/$part.tar.gz because its size in bytes $size"
+    echo "does not equal the size of one of the archives."
+    rm $data/$part.tar.gz
+  else
+    echo "$data/$part.tar.gz exists and appears to be complete."
+  fi
+fi
+
+if [ ! -f $data/$part.tar.gz ]; then
+  if ! which wget >/dev/null; then
+    echo "$0: wget is not installed."
+    exit 1
+  fi
+  full_url=$url/$part.tar.gz
+  echo "$0: downloading data from $full_url.  This may take some time, please be patient."
+
+  if ! wget -P $data --no-check-certificate $full_url; then
+    echo "$0: error executing wget $full_url"
+    exit 1
+  fi
+fi
+
+if ! tar -C $data -xvzf $data/$part.tar.gz; then
+  echo "$0: error un-tarring archive $data/$part.tar.gz"
+  exit 1
+fi
+
+touch $data/LibriSpeech/$part/.complete
+
+echo "$0: Successfully downloaded and un-tarred $data/$part.tar.gz"
+
+if $remove_archive; then
+  echo "$0: removing $data/$part.tar.gz file since --remove-archive option was supplied."
+  rm $data/$part.tar.gz
+fi

egs/librispeech_100h/conformer/run.sh

@@ -3,8 +3,8 @@
 . ./path.sh || exit 1;
 
 # machines configuration
-CUDA_VISIBLE_DEVICES="0,1,2,3,4,5,6,7"
-gpu_num=8
+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
@@ -16,30 +16,26 @@ infer_cmd=utils/run.pl
 feats_dir="../DATA" #feature output dictionary
 exp_dir="."
 lang=en
-dumpdir=dump/fbank
-feats_type=fbank
 token_type=bpe
-dataset_type=large
-scp=feats.scp
-type=kaldi_ark
-stage=3
-stop_stage=4
+type=sound
+scp=wav.scp
+stage=1
+stop_stage=1
 
 # feature configuration
 feats_dim=80
-sample_frequency=16000
-nj=100
-speed_perturb="0.9,1.0,1.1"
+nj=64
 
 # data
-data_librispeech=
+raw_data=
+data_url=www.openslr.org/resources/12
 
 # bpe model
 nbpe=5000
 bpemode=unigram
 
 # exp tag
-tag=""
+tag="exp1"
 
 . utils/parse_options.sh || exit 1;
 
@@ -54,8 +50,7 @@ valid_set=dev
 test_sets="test_clean test_other dev_clean dev_other"
 
 asr_config=conf/train_asr_conformer.yaml
-#asr_config=conf/train_asr_conformer_uttnorm.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_config=conf/decode_asr_transformer_beam60_ctc0.3.yaml
@@ -73,6 +68,14 @@ else
     _ngpu=0
 fi
 
+
+if [ ${stage} -le -1 ] && [ ${stop_stage} -ge -1 ]; then
+    echo "stage -1: Data Download"
+    for part in dev-clean test-clean dev-other test-other train-clean-100; do
+        local/download_and_untar.sh ${raw_data} ${data_url} ${part}
+    done
+fi
+
 if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
     echo "stage 0: Data preparation"
     # Data preparation