From d29efb7345db9dd61dd98c8116e4aa704226783f Mon Sep 17 00:00:00 2001 From: jinzr Date: Wed, 8 Nov 2023 10:20:56 +0800 Subject: [PATCH] Update prepare_lm_training_data.py --- egs/multi_zh-hans/ASR/local/prepare_lm_training_data.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/egs/multi_zh-hans/ASR/local/prepare_lm_training_data.py b/egs/multi_zh-hans/ASR/local/prepare_lm_training_data.py index 41638cd82..95ee982bd 100755 --- a/egs/multi_zh-hans/ASR/local/prepare_lm_training_data.py +++ b/egs/multi_zh-hans/ASR/local/prepare_lm_training_data.py @@ -102,6 +102,8 @@ def main(): if line == "": break line = tokenize_by_CJK_char(line) + if line == "": + continue if step and processed % step == 0: logging.info(f"Processed number of lines: {processed} ")