I am trying to adapt the WSJ acoustic model that comes with Sphinx4.
WSJ_8gau_13dCep_16k_40mel_130Hz_6800Hz. I was wondering if there is a
feat.params file for it as sphinx_fe uses it to generate the acoustic feature
files. If there isn't a feat.params file available is there a way around the
problem? Sorry very new to this. Thanks!
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hi,
I am trying to adapt the WSJ acoustic model that comes with Sphinx4.
WSJ_8gau_13dCep_16k_40mel_130Hz_6800Hz. I was wondering if there is a
feat.params file for it as sphinx_fe uses it to generate the acoustic feature
files. If there isn't a feat.params file available is there a way around the
problem? Sorry very new to this. Thanks!
sphinx_fe can generate params without feat.params
just use sphinx_fe without params
The options used are actually defaults:
-alpha 0.97
-dither yes
-doublebw no
-nfilt 40
-ncep 13
-lowerf 133.33334
-upperf 6855.4976
-nfft 512
-wlen 0.0256