Difference between revisions of "IRSTLM"
Jump to navigation
Jump to search
Naan Dhaan (talk | contribs) m (Updating installation steps) |
Naan Dhaan (talk | contribs) m (common issue) |
||
Line 14: | Line 14: | ||
make install |
make install |
||
</pre> |
</pre> |
||
if you get <code>stdlib.h</code> error, see https://github.com/irstlm-team/irstlm/issues/22 |
|||
== Make a language model == |
== Make a language model == |
||
<pre> |
<pre> |
Revision as of 08:02, 1 August 2021
IRSTLM is a free and open source exact statistical language model using memory-mapping. The language models are compatible with those created with the closed-source SRILM Tooolkit.
See the homepage at https://hlt-mt.fbk.eu/technologies/irstlm
Installation
see https://github.com/irstlm-team/irstlm or
svn checkout svn://svn.code.sf.net/p/irstlm/code/trunk irstlm cd irstlm cmake -G "Unix Makefiles" -DCMAKE_INSTALL_PREFIX=/path/prefix make -j4 make install
if you get stdlib.h
error, see https://github.com/irstlm-team/irstlm/issues/22
Make a language model
# only if you specified /path/prefix previously export PATH=$PATH:/path/prefix/bin build-lm.sh -i incorpus.txt -o out.lm.gz -t tmp/
See also
- Moses (includes alternative LM system KenLM)
- Using GIZA++
- RandLM - a randomised LM, based on Bloom Filters