From 810046e3df4910c8f5c1a90e4b53aca45b3397e8 Mon Sep 17 00:00:00 2001
From: wuhongsheng <664116298@qq.com>
Date: 星期一, 01 七月 2024 10:42:58 +0800
Subject: [PATCH] 优化merge segments 参数，解决新闻联播男女主持人“晚上好”合并一个speakid问题 (#1861)
---
examples/wenetspeech/conformer/run.sh | 2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/examples/wenetspeech/conformer/run.sh b/examples/wenetspeech/conformer/run.sh
index 0503a9e..6ae995a 100755
--- a/examples/wenetspeech/conformer/run.sh
+++ b/examples/wenetspeech/conformer/run.sh
@@ -92,7 +92,7 @@
echo "<blank>" > ${token_list}
echo "<s>" >> ${token_list}
echo "</s>" >> ${token_list}
- utils/text2token.py -s 1 -n 1 --space "" --text_format "jsonl" ${feats_dir}/data/$train_set/audio_datasets.jsonl | 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}
echo "<unk>" >> ${token_list}
fi
--
Gitblit v1.9.1