Hi,

in doc/s3_overview.html is mentioned that the sphinx3 decoder is only feasible to decode continous models.

The training scripts of SphinxTrain are ready to train semiconinous model.

So, what I am looking for are some scripts to train continous models to train models for the Spinx3 decoder.
The executables to do this should be all present and the way to do this is described in http://www-2.cs.cmu.edu/~rsingh/sphinxman/scriptman1.html

Did someone build scripts according to this? Or am I wrong and the semicontinous models can be used with sphinx3.3?

Dirk