For my current config, I am using:
config = cmd_ln_init(NULL , ps_args(), TRUE,
"-hmm", hmmPath,
"-lm", lmPath,
"-dict", dictPath,
"-samprate", "8000",
NULL);
Is it better to pass this config to cmd_ln_init32_r() or add "-frate" to my
first cmd_ln_init? Also, to clarify, if I specify -frate 100 am I getting 100
frames per second?
Thanks for the quick response!
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Is it better to pass this config to cmd_ln_init32_r() or add "-frate" to my
first cmd_ln_init?
cmd_ln_int32_r retrieves the configured value, it doesn't update it. frate is
configured in cmd_ln_init. 100 is a default value. It means 100 frame per
second.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hello,
I am trying to get the timestamp for each word in a given utterance by use of
the function:
void ps_seg_frames(ps_seg_t seg, int out_sf, int *out_ef);
This is working great except I don't know the context for out_sf (start frame)
and out_ef (end frame).
How can I know or calculate how many frames per second pocketsphinx is using
for recognition?
Thanks!
It's configured with frate:
For my current config, I am using:
config = cmd_ln_init(NULL , ps_args(), TRUE,
"-hmm", hmmPath,
"-lm", lmPath,
"-dict", dictPath,
"-samprate", "8000",
NULL);
Is it better to pass this config to cmd_ln_init32_r() or add "-frate" to my
first cmd_ln_init? Also, to clarify, if I specify -frate 100 am I getting 100
frames per second?
Thanks for the quick response!
cmd_ln_int32_r retrieves the configured value, it doesn't update it. frate is
configured in cmd_ln_init. 100 is a default value. It means 100 frame per
second.