When I downloaded the "cmusphinx-de-ptm-voxforge-5.2.tar.gz", I was really confused when reading the feat.params file. It says "-feat 1s_c_d_dd", which is used by continuous models if I got this right (Source: https://cmusphinx.github.io/wiki/acousticmodeltypes/). But the model is supposed to be a PTM model. Can someone please explain this to me?
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
It is perfectly fine to have that in PTM model, the wiki is not very clean about it. To work with that model in sphinx4 you need to add a line '-model ptm' into feat.params file.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hello everyone,
I am currently working with Sphinx4 and wanted to try out both continuous and ptm German acoustic models. I downloaded them from here:
https://sourceforge.net/projects/cmusphin/file/Acoustic%20and%20Language%20Models/German/
When I downloaded the "cmusphinx-de-ptm-voxforge-5.2.tar.gz", I was really confused when reading the feat.params file. It says "-feat 1s_c_d_dd", which is used by continuous models if I got this right (Source: https://cmusphinx.github.io/wiki/acousticmodeltypes/). But the model is supposed to be a PTM model. Can someone please explain this to me?
The model is PTM and it is really old. You can find more recent models at
https://github.com/gooofy/zamia-speech/
Thank you very much! I checked out their PTM model, but again the feat.params say:
-lowerf 130
-upperf 6800
-nfilt 25
-transform dct
-lifter 22
-feat 1s_c_d_dd
-svspec 0-12/13-25/26-38
-agc none
-cmn current
-varnorm no
It is perfectly fine to have that in PTM model, the wiki is not very clean about it. To work with that model in sphinx4 you need to add a line '-model ptm' into feat.params file.
Thank you very much!