From 23a749f956affdfe078f8b8eeaa59b830efb5ff7 Mon Sep 17 00:00:00 2001
From: 嘉渊 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期四, 11 五月 2023 17:55:08 +0800
Subject: [PATCH] update repo

---
 egs/aishell/data2vec_transformer_finetune/run.sh                                                    |  116 +++++-----------
 /dev/null                                                                                           |   53 -------
 egs/aishell/data2vec_transformer_finetune/conf/train_asr_transformer_12e_6d_3072_768.yaml           |   39 +++-
 egs/aishell/data2vec_transformer_finetune/local/download_and_untar.sh                               |  105 +++++++++++++++
 egs/aishell/data2vec_paraformer_finetune/local/download_and_untar.sh                                |  105 +++++++++++++++
 egs/aishell/data2vec_paraformer_finetune/conf/train_asr_paraformer_transformer_12e_6d_3072_768.yaml |    2 
 6 files changed, 273 insertions(+), 147 deletions(-)

diff --git a/egs/aishell/data2vec_paraformer_finetune/conf/train_asr_paraformer_transformer_12e_6d_3072_768.yaml b/egs/aishell/data2vec_paraformer_finetune/conf/train_asr_paraformer_transformer_12e_6d_3072_768.yaml
index bc68ed2..287b088 100644
--- a/egs/aishell/data2vec_paraformer_finetune/conf/train_asr_paraformer_transformer_12e_6d_3072_768.yaml
+++ b/egs/aishell/data2vec_paraformer_finetune/conf/train_asr_paraformer_transformer_12e_6d_3072_768.yaml
@@ -30,7 +30,6 @@
     require_same_masks: true
     mask_dropout: 0
 
-
 # decoder related
 decoder: paraformer_decoder_san
 decoder_conf:
@@ -53,6 +52,7 @@
     lfr_m: 1
     lfr_n: 1
 
+# hybrid CTC/attention
 model: paraformer
 model_conf:
     ctc_weight: 0.3
diff --git a/egs/aishell/data2vec_paraformer_finetune/local/download_and_untar.sh b/egs/aishell/data2vec_paraformer_finetune/local/download_and_untar.sh
new file mode 100755
index 0000000..d982559
--- /dev/null
+++ b/egs/aishell/data2vec_paraformer_finetune/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/data2vec_paraformer_finetune/local/prepare_data.sh b/egs/aishell/data2vec_paraformer_finetune/local/prepare_data.sh
deleted file mode 100755
index 77791f9..0000000
--- a/egs/aishell/data2vec_paraformer_finetune/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/data2vec_transformer_finetune/conf/train_asr_transformer_12e_6d_3072_768.yaml b/egs/aishell/data2vec_transformer_finetune/conf/train_asr_transformer_12e_6d_3072_768.yaml
index 5bc5236..ad3ad2e 100644
--- a/egs/aishell/data2vec_transformer_finetune/conf/train_asr_transformer_12e_6d_3072_768.yaml
+++ b/egs/aishell/data2vec_transformer_finetune/conf/train_asr_transformer_12e_6d_3072_768.yaml
@@ -30,25 +30,28 @@
   require_same_masks: true
   mask_dropout: 0
 
+# frontend related
+frontend: wav_frontend
+frontend_conf:
+    fs: 16000
+    window: hamming
+    n_mels: 80
+    frame_length: 25
+    frame_shift: 10
+    lfr_m: 1
+    lfr_n: 1
+
 # hybrid CTC/attention
 model_conf:
     ctc_weight: 1.0
     lsm_weight: 0.1     # label smoothing option
     length_normalized_loss: false
 
-# for logger
-log_interval: 50
-
-# minibatch related
-batch_type: length
-batch_bins: 16000
-num_workers: 16
-
 # optimization related
 accum_grad: 1
 grad_clip: 5
 patience: none
-max_epoch: 50
+max_epoch: 150
 val_scheduler_criterion:
     - valid
     - acc
@@ -57,8 +60,6 @@
     - cer_ctc
     - min
 keep_nbest_models: 10
-unused_parameters: true
-normalize: None
 
 # NoamLR is deprecated. Use WarmupLR.
 # The following is equivalent setting for NoamLR:
@@ -92,4 +93,18 @@
     time_mask_width_range:
     - 0
     - 40
-    num_time_mask: 2
\ No newline at end of file
+    num_time_mask: 2
+
+dataset_conf:
+    shuffle: True
+    shuffle_conf:
+        shuffle_size: 2048
+        sort_size: 500
+    batch_conf:
+        batch_type: token
+        batch_size: 25000
+    num_workers: 8
+
+log_interval: 50
+unused_parameters: true
+normalize: None
\ No newline at end of file
diff --git a/egs/aishell/data2vec_transformer_finetune/local/download_and_untar.sh b/egs/aishell/data2vec_transformer_finetune/local/download_and_untar.sh
new file mode 100755
index 0000000..d982559
--- /dev/null
+++ b/egs/aishell/data2vec_transformer_finetune/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/data2vec_transformer_finetune/local/prepare_data.sh b/egs/aishell/data2vec_transformer_finetune/local/prepare_data.sh
deleted file mode 100755
index 77791f9..0000000
--- a/egs/aishell/data2vec_transformer_finetune/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/data2vec_transformer_finetune/run.sh b/egs/aishell/data2vec_transformer_finetune/run.sh
index 26222e6..65dd71b 100755
--- a/egs/aishell/data2vec_transformer_finetune/run.sh
+++ b/egs/aishell/data2vec_transformer_finetune/run.sh
@@ -8,33 +8,30 @@
 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=5
+njob=1
 train_cmd=utils/run.pl
 infer_cmd=utils/run.pl
 
 # general configuration
-feats_dir="../DATA" #feature output dictionary, for large data
+feats_dir="../DATA" #feature output dictionary
 exp_dir="."
 lang=zh
-dumpdir=dump/fbank
-feats_type=fbank
 token_type=char
-scp=feats.scp
-type=kaldi_ark
-stage=0
+type=sound
+scp=wav.scp
+stage=3
 stop_stage=4
 
 # feature configuration
 feats_dim=80
-sample_frequency=16000
-nj=32
-speed_perturb="0.9,1.0,1.1"
+nj=64
 
 # data
-data_aishell=
+raw_data=
+data_url=www.openslr.org/resources/33
 
 # exp tag
-tag=""
+tag="exp1"
 
 model_name=damo/speech_data2vec_pretrain-zh-cn-aishell2-16k-pytorch
 init_param="$HOME/.cache/modelscope/hub/$model_name/basemodel.pb"
@@ -52,10 +49,10 @@
 test_sets="dev test"
 
 asr_config=conf/train_asr_transformer_12e_6d_3072_768.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.cer_ctc.ave_10best.pb
+inference_config=conf/decode_asr_transformer_noctc_1best.yaml
+inference_asr_model=valid.acc.ave_10best.pb
 
 # you can set gpu num for decoding here
 gpuid_list=$CUDA_VISIBLE_DEVICES  # set gpus for decoding, the same as training stage by default
@@ -69,10 +66,16 @@
     _ngpu=0
 fi
 
+if [ ${stage} -le -1 ] && [ ${stop_stage} -ge -1 ]; then
+    echo "stage -1: Data Download"
+    local/download_and_untar.sh ${raw_data} ${data_url} data_aishell
+    local/download_and_untar.sh ${raw_data} ${data_url} resource_aishell
+fi
+
 if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
     echo "stage 0: Data preparation"
     # Data preparation
-    local/aishell_data_prep.sh ${data_aishell}/data_aishell/wav ${data_aishell}/data_aishell/transcript ${feats_dir}
+    local/aishell_data_prep.sh ${raw_data}/data_aishell/wav ${raw_data}/data_aishell/transcript ${feats_dir}
     for x in train dev test; do
         cp ${feats_dir}/data/${x}/text ${feats_dir}/data/${x}/text.org
         paste -d " " <(cut -f 1 -d" " ${feats_dir}/data/${x}/text.org) <(cut -f 2- -d" " ${feats_dir}/data/${x}/text.org | tr -d " ") \
@@ -82,46 +85,9 @@
     done
 fi
 
-feat_train_dir=${feats_dir}/${dumpdir}/train; mkdir -p ${feat_train_dir}
-feat_dev_dir=${feats_dir}/${dumpdir}/dev; mkdir -p ${feat_dev_dir}
-feat_test_dir=${feats_dir}/${dumpdir}/test; mkdir -p ${feat_test_dir}
 if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
-    echo "stage 1: Feature Generation"
-    # compute fbank features
-    fbankdir=${feats_dir}/fbank
-    utils/compute_fbank.sh --cmd "$train_cmd" --nj $nj --feats_dim ${feats_dim} --sample_frequency ${sample_frequency} --speed_perturb ${speed_perturb} \
-        ${feats_dir}/data/train ${exp_dir}/exp/make_fbank/train ${fbankdir}/train
-    utils/fix_data_feat.sh ${fbankdir}/train
-    utils/compute_fbank.sh --cmd "$train_cmd" --nj $nj --feats_dim ${feats_dim} --sample_frequency ${sample_frequency} \
-        ${feats_dir}/data/dev ${exp_dir}/exp/make_fbank/dev ${fbankdir}/dev
-    utils/fix_data_feat.sh ${fbankdir}/dev
-    utils/compute_fbank.sh --cmd "$train_cmd" --nj $nj --feats_dim ${feats_dim} --sample_frequency ${sample_frequency} \
-        ${feats_dir}/data/test ${exp_dir}/exp/make_fbank/test ${fbankdir}/test
-    utils/fix_data_feat.sh ${fbankdir}/test
-     
-    # compute global cmvn
-    utils/compute_cmvn.sh --cmd "$train_cmd" --nj $nj --feats_dim ${feats_dim} \
-        ${fbankdir}/train ${exp_dir}/exp/make_fbank/train
-
-    # apply cmvn 
-    utils/apply_cmvn.sh --cmd "$train_cmd" --nj $nj \
-        ${fbankdir}/train ${fbankdir}/train/cmvn.json ${exp_dir}/exp/make_fbank/train ${feat_train_dir}
-    utils/apply_cmvn.sh --cmd "$train_cmd" --nj $nj \
-        ${fbankdir}/dev ${fbankdir}/train/cmvn.json ${exp_dir}/exp/make_fbank/dev ${feat_dev_dir}
-    utils/apply_cmvn.sh --cmd "$train_cmd" --nj $nj \
-        ${fbankdir}/test ${fbankdir}/train/cmvn.json ${exp_dir}/exp/make_fbank/test ${feat_test_dir}
-    
-    cp ${fbankdir}/train/text ${fbankdir}/train/speech_shape ${fbankdir}/train/text_shape ${feat_train_dir}
-    cp ${fbankdir}/dev/text ${fbankdir}/dev/speech_shape ${fbankdir}/dev/text_shape ${feat_dev_dir}
-    cp ${fbankdir}/test/text ${fbankdir}/test/speech_shape ${fbankdir}/test/text_shape ${feat_test_dir}
-
-    utils/fix_data_feat.sh ${feat_train_dir}
-    utils/fix_data_feat.sh ${feat_dev_dir}
-    utils/fix_data_feat.sh ${feat_test_dir}
-
-    #generate ark list 
-    utils/gen_ark_list.sh --cmd "$train_cmd" --nj $nj ${feat_train_dir} ${fbankdir}/train ${feat_train_dir}
-    utils/gen_ark_list.sh --cmd "$train_cmd" --nj $nj ${feat_dev_dir} ${fbankdir}/dev ${feat_dev_dir}
+    echo "stage 1: Feature and CMVN Generation"
+    utils/compute_cmvn.sh --cmd "$train_cmd" --nj $nj --feats_dim ${feats_dim} ${feats_dir}/data/${train_set}
 fi
 
 token_list=${feats_dir}/data/${lang}_token_list/char/tokens.txt
@@ -129,35 +95,27 @@
 if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
     echo "stage 2: Dictionary Preparation"
     mkdir -p ${feats_dir}/data/${lang}_token_list/char/
-   
+
     echo "make a dictionary"
     echo "<blank>" > ${token_list}
     echo "<s>" >> ${token_list}
     echo "</s>" >> ${token_list}
-    utils/text2token.py -s 1 -n 1 --space "" ${feats_dir}/data/train/text | cut -f 2- -d" " | tr " " "\n" \
+    utils/text2token.py -s 1 -n 1 --space "" ${feats_dir}/data/$train_set/text | cut -f 2- -d" " | tr " " "\n" \
         | sort | uniq | grep -a -v -e '^\s*$' | awk '{print $0}' >> ${token_list}
-    num_token=$(cat ${token_list} | wc -l)
     echo "<unk>" >> ${token_list}
-    vocab_size=$(cat ${token_list} | wc -l)
-    awk -v v=,${vocab_size} '{print $0v}' ${feat_train_dir}/text_shape > ${feat_train_dir}/text_shape.char
-    awk -v v=,${vocab_size} '{print $0v}' ${feat_dev_dir}/text_shape > ${feat_dev_dir}/text_shape.char
-    mkdir -p ${feats_dir}/asr_stats_fbank_zh_char/train 
-    mkdir -p ${feats_dir}/asr_stats_fbank_zh_char/dev
-    cp ${feat_train_dir}/speech_shape ${feat_train_dir}/text_shape ${feat_train_dir}/text_shape.char ${feats_dir}/asr_stats_fbank_zh_char/train
-    cp ${feat_dev_dir}/speech_shape ${feat_dev_dir}/text_shape ${feat_dev_dir}/text_shape.char ${feats_dir}/asr_stats_fbank_zh_char/dev
 fi
 
 # Training Stage
 world_size=$gpu_num  # run on one machine
 if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
     echo "stage 3: Training"
-    python utils/download_model.py  --model_name ${model_name}  # download pretrained model on ModelScope
+     python utils/download_model.py  --model_name ${model_name}  # download pretrained model on ModelScope
     mkdir -p ${exp_dir}/exp/${model_dir}
     mkdir -p ${exp_dir}/exp/${model_dir}/log
     INIT_FILE=${exp_dir}/exp/${model_dir}/ddp_init
     if [ -f $INIT_FILE ];then
         rm -f $INIT_FILE
-    fi 
+    fi
     init_method=file://$(readlink -f $INIT_FILE)
     echo "$0: init method is $init_method"
     for ((i = 0; i < $gpu_num; ++i)); do
@@ -165,27 +123,22 @@
             rank=$i
             local_rank=$i
             gpu_id=$(echo $CUDA_VISIBLE_DEVICES | cut -d',' -f$[$i+1])
-            asr_train.py \
+            train.py \
+                --task_name asr \
                 --gpu_id $gpu_id \
                 --use_preprocessor true \
                 --token_type char \
                 --token_list $token_list \
-                --train_data_path_and_name_and_type ${feats_dir}/${dumpdir}/${train_set}/${scp},speech,${type} \
-                --train_data_path_and_name_and_type ${feats_dir}/${dumpdir}/${train_set}/text,text,text \
-                --train_shape_file ${feats_dir}/asr_stats_fbank_zh_char/${train_set}/speech_shape \
-                --train_shape_file ${feats_dir}/asr_stats_fbank_zh_char/${train_set}/text_shape.char \
-                --valid_data_path_and_name_and_type ${feats_dir}/${dumpdir}/${valid_set}/${scp},speech,${type} \
-                --valid_data_path_and_name_and_type ${feats_dir}/${dumpdir}/${valid_set}/text,text,text \
-                --valid_shape_file ${feats_dir}/asr_stats_fbank_zh_char/${valid_set}/speech_shape \
-                --valid_shape_file ${feats_dir}/asr_stats_fbank_zh_char/${valid_set}/text_shape.char  \
+                --data_dir ${feats_dir}/data \
+                --train_set ${train_set} \
+                --valid_set ${valid_set} \
                 --init_param ${init_param} \
+                --cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
                 --resume true \
                 --output_dir ${exp_dir}/exp/${model_dir} \
                 --config $asr_config \
-                --input_size $feats_dim \
                 --ngpu $gpu_num \
                 --num_worker_count $count \
-                --multiprocessing_distributed true \
                 --dist_init_method $init_method \
                 --dist_world_size $world_size \
                 --dist_rank $rank \
@@ -208,7 +161,7 @@
             exit 0
         fi
         mkdir -p "${_logdir}"
-        _data="${feats_dir}/${dumpdir}/${dset}"
+        _data="${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")
@@ -229,11 +182,12 @@
                 --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 \
+                --mode paraformer \
                 ${_opts}
 
         for f in token token_int score text; do
@@ -249,4 +203,4 @@
         tail -n 3 ${_dir}/text.cer > ${_dir}/text.cer.txt
         cat ${_dir}/text.cer.txt
     done
-fi
+fi
\ No newline at end of file

--
Gitblit v1.9.1