2004-07-29 CMU Sphinx2-0.5.  
http://cmusphinx.org

This is Sphinx 2, one of Carnegie Mellon University's open source
large vocabulary, speaker-independent continuous speech recognition
engine. Please see the LICENSE file for terms of use.

THIS IS A RESEARCH SYSTEM.  This is also an early release of a
research system.  We know the APIs and function names are likely to
change, and that several tools need to be made available to make this
all complete.  With your help and contributions, this can progress in
response to the needs and patches provided.

To compile:

-in a unix-like environment (such as linux, solaris etc):

% configure
% make clean all
% make test
% make install

Once the system is built and installed, try running sphinx2-test to
see if the system works for a pre-recorded file.  Then you may want to
try sphinx2-simple, and the perl script sphinx2-demo.  You may have to
change the bang path to perl at the top.

-in MS Windows (TM), under MS Visual C++ 6.0 (or better):

-load sphinx2.dsw (located at the top level directory)
-compile minimally the project 'sphinx2-continuous'
-in a command prompt (Follow the menus "Start" -> "Run" -> "cmd"), cd
to the location where you installed sphinx2 (e.g., c:\sphinx2-0.5)
-run .\win32\batch\sphinx-test.bat

MS Visual Studio will build the executables under .\bin\Release or
.\bin\Debug (depending on the version you choose on MS Visual Studio),
and the libraries under .\lib\Release or .\lib\Build.

When successfully built, either in unix/linux or in Windows,
sphinx2-test (or sphinx2-test.bat, in Windows) should run
sphinx2-continuous (or sphinx2-continuous.exe) over an example
utterance of "go forward ten meters".

Please see the web site at

   http://cmusphinx.org

for up-to-date information.

