‹ projects

vmc

a voice model creator for CMU Sphinx
Log | Files | Refs | README | LICENSE

commit fb2c9e70a8b24dac467ab63be627c1b60e300fae
parent fe767fc1f2d887aedddc456c6bb333def66f0010
Author: umhau <umhau@alum.gcc.edu>
Date:   Wed,  5 Jul 2017 23:38:55 -0400

the python pocketsphinx voice model doesn't include the mixture_weights file.  I don't know what it is, but I'm copying the CMU Sphinx version.

Diffstat:
Mvmc | 19+++++++++++++++++++
1 file changed, 19 insertions(+), 0 deletions(-)

diff --git a/vmc b/vmc @@ -63,6 +63,21 @@ fi current_number_of_recordings="0" # changed below, if there are any. +# FUNCTIONS =================================================================== + +make_sure_model_files_exist() { + + for model_file in /opt/vmc/lib/en-us/* + do + local filename=$(basename $model_file) + if [ ! -f "$model_location/$filename" ] + then + sudo cp $model_file "$model_location/$filename" + fi + done + +} + # COMMANDS ==================================================================== # remove vmc ------------------------------------------------------------------ @@ -125,6 +140,10 @@ fi bash /opt/vmc/lib/move_ps_files.sh -into_lib +# Make sure all the files exist that are needed ------------------------------- + +make_sure_model_files_exist + # PRODUCE DERIVATIVE FILES ---------------------------------------------------- # These are recreated for all audio files, regardless of whether this is a new # collection of recordings or just adding to an old one. Simpler that way.