Hi All:
I am trying to train a model to recognize some few words and after recording audio
(.wav 16kHz mono ) files I'm using the command:
..\first>perl scripts_pl\make_feats.pl -ctl etc\first_train.fileids
then the process arrive to a line as follows:
INFO: ........\src\programs\wave2feat.c(139): wav\hsn\hsn01.wav
and at this point the CPU usage becomes 100% and don't create any feature files and
still in this line
I wait this line for more than 2 hours but nothing happen.
please and very quickly please: if someone can help me to reply me and tell me
what's the wrong.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hi All:
I am trying to train a model to recognize some few words and after recording audio
(.wav 16kHz mono ) files I'm using the command:
..\first>perl scripts_pl\make_feats.pl -ctl etc\first_train.fileids
then the process arrive to a line as follows:
INFO: ........\src\programs\wave2feat.c(139): wav\hsn\hsn01.wav
and at this point the CPU usage becomes 100% and don't create any feature files and
still in this line
I wait this line for more than 2 hours but nothing happen.
please and very quickly please: if someone can help me to reply me and tell me
what's the wrong.
thanks very much.
I solved the problem before your reply
and it's exactly what you mention
You didn't set up sound params properly in etc/sphinx_train.cfg. Specifically, the type of the file. Make sure you pass -mswav yes to the wave2feat.