From 6f7e27eb7c2d0a7649ec8f14d167c8da8e29f906 Mon Sep 17 00:00:00 2001
From: jmwang66 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期二, 16 五月 2023 15:07:20 +0800
Subject: [PATCH] Merge pull request #518 from alibaba-damo-academy/dev_wjm2

---
 egs/aishell/paraformerbert/local/aishell_data_prep.sh |   23 ++++++++++++-----------
 1 files changed, 12 insertions(+), 11 deletions(-)

diff --git a/egs/aishell/paraformerbert/local/aishell_data_prep.sh b/egs/aishell/paraformerbert/local/aishell_data_prep.sh
index b6ea36b..83f489b 100755
--- a/egs/aishell/paraformerbert/local/aishell_data_prep.sh
+++ b/egs/aishell/paraformerbert/local/aishell_data_prep.sh
@@ -5,19 +5,20 @@
 
 #. ./path.sh || exit 1;
 
-if [ $# != 2 ]; then
-  echo "Usage: $0 <audio-path> <text-path>"
-  echo " $0 /export/a05/xna/data/data_aishell/wav /export/a05/xna/data/data_aishell/transcript"
+if [ $# != 3 ]; then
+  echo "Usage: $0 <audio-path> <text-path> <output-path>"
+  echo " $0 /export/a05/xna/data/data_aishell/wav /export/a05/xna/data/data_aishell/transcript data"
   exit 1;
 fi
 
 aishell_audio_dir=$1
 aishell_text=$2/aishell_transcript_v0.8.txt
+output_dir=$3
 
-train_dir=data/local/train
-dev_dir=data/local/dev
-test_dir=data/local/test
-tmp_dir=data/local/tmp
+train_dir=$output_dir/data/local/train
+dev_dir=$output_dir/data/local/dev
+test_dir=$output_dir/data/local/test
+tmp_dir=$output_dir/data/local/tmp
 
 mkdir -p $train_dir
 mkdir -p $dev_dir
@@ -53,12 +54,12 @@
   sort -u $dir/transcripts.txt > $dir/text
 done
 
-mkdir -p data/train data/dev data/test
+mkdir -p $output_dir/data/train $output_dir/data/dev $output_dir/data/test
 
 for f in wav.scp text; do
-  cp $train_dir/$f data/train/$f || exit 1;
-  cp $dev_dir/$f data/dev/$f || exit 1;
-  cp $test_dir/$f data/test/$f || exit 1;
+  cp $train_dir/$f $output_dir/data/train/$f || exit 1;
+  cp $dev_dir/$f $output_dir/data/dev/$f || exit 1;
+  cp $test_dir/$f $output_dir/data/test/$f || exit 1;
 done
 
 echo "$0: AISHELL data preparation succeeded"

--
Gitblit v1.9.1