Commit 3245cb92 authored by Ho Yin Chan's avatar Ho Yin Chan
Browse files

trunk/egs/hkust: add alternative chinese character scoring scripts; if the...

trunk/egs/hkust: add alternative chinese character scoring scripts; if the wordlist (words in the lexicon) used by the decoder is a subset of the words in 195k_chinese_word2char_map (1st column of 195k_chinese_word2char_map contains chinese words, 2nd to end column fields are corresponding seperated chinese characters), scoring with score_basic_ext.sh will give pure chinese character error rate

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@2748 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8
parent dc37f537
#!/bin/bash
# Copyright Johns Hopkins University (Author: Daniel Povey) 2012-2013.
# Hong Kong University of Science and Technology (Ricky Chan). Apache 2.0.
#
# An alternative chinese character scoring script; If the wordlist (words in the lexicon) used by the decoder is a subset of the words in 195k_chinese_word2char_map (1st column of 195k_chinese_word2char_map contains chinese words, 2nd to end column fields are corresponding seperated chinese characters), scoring with score_basic_ext.sh will give pure chinese character error rate
# begin configuration section.
cmd=run.pl
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment