Hi guys,
I have been tring to adapt the default acoustic model with following this article
Right now I am on the "Accumulating observation counts" step.
When I write these code blocks :
WARN: "mod_inv.c", line 353: Number of tied states in mdef file 5126 differs fro
m the number of mixtures 5138 in en-us/mixture_weights, do files belong to th
e same model?
FATAL: "mod_inv.c", line 358: Number of feature streams in mixture_weights file
1 differs from the configured value 3, check the command line options
I have downloaded the mixture_weights file inside of cmusphinx-en-us-ptm-5.2.tar.gz from this link.
I have downloaded cmusphinx-en-us-ptm-5.2.tar.gz file because the article says that.
Anybody help me ?
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hi guys,
I have been tring to adapt the default acoustic model with following this article
Right now I am on the "Accumulating observation counts" step.
When I write these code blocks :
it gives errors.
I have downloaded the mixture_weights file inside of cmusphinx-en-us-ptm-5.2.tar.gz from this link.
I have downloaded cmusphinx-en-us-ptm-5.2.tar.gz file because the article says that.
Anybody help me ?
You mistakenly took mixture_weights from cmusphinx-en-us-5.2.tar.gz not from cmusphinx-en-us-ptm-5.2.tar.gz.