Data compression using LSTM
Switch branches/tags
Nothing to show
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Type Name Latest commit message Commit time
Failed to load latest commit information.
build adding empty build directory May 31, 2017
dictionary changes from cmix v14 Oct 25, 2017
src imported cmix changes May 19, 2018
.gitignore adding empty build directory May 31, 2017
COPYING readme May 10, 2017 -O3 Jun 16, 2017
makefile imported cmix changes May 19, 2018


Data compression using LSTM. This project uses the same LSTM and preprocessing code as cmix ( All of the other cmix models are removed, so the compression is performed using only LSTM.

lstm-compress is free software distributed under the GNU General Public License.

In Linux or OS X, use "make" to compile lstm-compress using g++. In Windows, lstm-compress can be compiled with MinGW ( or Cygwin (

When running lstm-compress, it is usually recommended to enable preprocessing with "dictionary/english.dic".

lstm-compress can only compress/decompress single files. To compress multiple files or directories, create an archive file using "tar" (or some similar tool).

For some files, preprocessing using "precomp" may improve compression: