getWordFreq(1) print word freq information from language model


getWordFreq [option]... -m slm-file -l lexicon


getWordFreq prints out the word string and its freq of all words in a language model.


-s corpus-size Specify the training corpus's size. The default corpus-size is 300000000 if not given.
Be verbose, output other information after word and freq for each line.
Give format for ervin.
-m slm-file
Specify language model file.
-l lexicon
Specify the lexicon file. A default lexicon could be found at /usr/share/sunpinyin-slm/dict.utf8.


Originally written by Phill.Zhang <[email protected]>. Currently maintained by Kov.Chai <[email protected]>.