GitLab

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@5114 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

trunk: standardizing all perl and python scripts to start with a shebang /usr/bin/env perl|python, and to be executable.  Minor script change to train_mono.sh to print better info in case of error.

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@5110 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@4732 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

trunk: merging sandbox/dan back to trunk.  Includes addition of recipe for the LibriSpeech corpus, and the capability to rescore lattices using ARPA language models that are too big to convert into FSTs.

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@4504 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

trunk: changing all the scoring scripts to use 'sctk' instead of 'sctk-2.4.0' as directory name (Makefile now creates soft link).  Note: this will unfortunately break existing setups, causing users to need to recompile in tools/

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@4354 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@4301 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@4282 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

trunk: Replace download server merlin, where used, with www.danielpovey.com (files on merlin disappeared).

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3246 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

trunk:egs/hkust update on chinese character error rate (CER) scoring script. Add --useword2charmap option and comments.

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@2872 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@2804 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

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

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, 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@2747 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@2746 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@2727 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

trunk/egs/hkust: subdict extraction script is modified for handling multiple pronunciations generation

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@2725 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@2719 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@1638 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@1634 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8