From 4d907718f39e2b0f7a0c714c2e3de289e742fc61 Mon Sep 17 00:00:00 2001 From: Carl <415692979@qq.com> Date: 星期四, 28 三月 2024 13:42:00 +0800 Subject: [PATCH] 修正commit 87b62d68957a2194b017a43b6c2a15424a05a984 引入的英文整句标点预测导致末尾两个单词中间的空格被删除的问题。 (#1556) --- runtime/docs/lm_train_tutorial.md | 3 ++- 1 files changed, 2 insertions(+), 1 deletions(-) diff --git a/runtime/docs/lm_train_tutorial.md b/runtime/docs/lm_train_tutorial.md index 7c6c5cb..65cecc2 100644 --- a/runtime/docs/lm_train_tutorial.md +++ b/runtime/docs/lm_train_tutorial.md @@ -6,6 +6,7 @@ ```shell # 涓嬭浇: 绀轰緥璁粌璇枡text銆乴exicon 鍜� am寤烘ā鍗曞厓units.txt wget https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/requirements/lm.tar.gz +# 濡傛灉鏄尮閰�8k鐨刟m妯″瀷锛屼娇鐢� https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/requirements/lm_8358.tar.gz tar -zxvf lm.tar.gz ``` @@ -24,8 +25,8 @@ python3 fst/generate_lexicon.py lm/corpus.dict lm/lexicon.txt lm/lexicon.out ``` -缂栬瘧TLG闇�瑕佷緷璧杅st鐨勭幆澧冿紝璇峰弬鑰冩枃妗e畨瑁協ts鐩稿叧鐜锛圼鐐瑰嚮姝ゅ](../onnxruntime/readme.md)锛� ## 缂栬瘧TLG.fst +缂栬瘧TLG闇�瑕佷緷璧杅st鐨勭幆澧冿紝璇峰弬鑰冩枃妗e畨瑁協ts鐩稿叧鐜锛圼鐐瑰嚮姝ゅ](../onnxruntime/readme.md)锛� ```shell # Compile the lexicon and token FSTs -- Gitblit v1.9.1