From 2e228a24815216d36cc6b3cce2f15fc88197a926 Mon Sep 17 00:00:00 2001
From: 嘉渊 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期五, 26 五月 2023 10:08:45 +0800
Subject: [PATCH] update repo
---
egs/wenetspeech/conformer/run.sh | 35 +++++++++++++++++++++++++----------
1 files changed, 25 insertions(+), 10 deletions(-)
diff --git a/egs/wenetspeech/conformer/run.sh b/egs/wenetspeech/conformer/run.sh
index 0945e66..9f6e4ae 100644
--- a/egs/wenetspeech/conformer/run.sh
+++ b/egs/wenetspeech/conformer/run.sh
@@ -72,15 +72,30 @@
if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
echo "stage 0: Data preparation"
# Data preparation
- local/data.sh "--set ${set}"
-# mkdir $feats_dir/data
-# mv $feats_dir/$train_set $feats_dir/data/$train_set
-# for x in $test_sets; do
-# mv $feats_dir/$x $feats_dir/data/
-# done
+# local/data.sh --set ${set} --nj $nj --data_dir $feats_dir --WENETSPEECH $raw_data --train_cmd $train_cmd
+ mkdir $feats_dir/data
+ mv $feats_dir/$train_set $feats_dir/data/$train_set
+ for x in $test_sets; do
+ mv $feats_dir/$x $feats_dir/data/
+ done
fi
-#if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
-# echo "stage 1: Feature and CMVN Generation"
-# utils/compute_cmvn.sh --fbankdir ${feats_dir}/data/${train_set} --cmd "$train_cmd" --nj $nj --feats_dim ${feats_dim} --config_file "$asr_config" --scale 0.1
-#fi
+if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
+ echo "stage 1: Feature and CMVN Generation"
+ utils/compute_cmvn.sh --fbankdir ${feats_dir}/data/${train_set} --cmd "$train_cmd" --nj $nj --feats_dim ${feats_dim} --config_file "$asr_config" --scale 0.1
+fi
+
+token_list=${feats_dir}/data/${lang}_token_list/$token_type/tokens.txt
+echo "dictionary: ${token_list}"
+if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
+ echo "stage 2: Dictionary Preparation"
+ mkdir -p ${feats_dir}/data/${lang}_token_list/$token_type/
+
+ 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_set/text | cut -f 2- -d" " | tr " " "\n" \
+ | sort | uniq | grep -a -v -e '^\s*$' | awk '{print $0}' >> ${token_list}
+ echo "<unk>" >> ${token_list}
+fi
--
Gitblit v1.9.1