Hi guys,
I have been following in this article to be able adap the default acoustic model. I am on "Creating transformation with MLLR" step.
However when I run the these code blocks :
Current configuration: [NAME][DEFLT][VALUE]
-accumdir .,
-cb2mllrfn .1cls. .1cls.
-cdonly no no
-example no no
-fullvar no no
-help no no
-meanfn aa/en-us/means
-mllradd yes yes
-mllrmult yes yes
-moddeffn
-outmllrfn mllr_matrix
-varfloor 1e-3 1.000000e-003
-varfn aa/en-us/variances
INFO: main.c(382): -- 1. Read input mean, (var) and accumulation.
INFO: s3gau_io.c(169): Read aa/en-us/means [5138x1x32 array]
INFO: main.c(397): Reading and accumulating counts from .
INFO: s3gau_io.c(386): Read ./gauden_counts with means with vars [42x3x128 vecto
r arrays]
FATAL: "main.c", line 412: n_mgau mismatch (5138 : 42)
Before I have looked for about this error in this forum. But I couldn't find any similar issue.
I hope that anyone can help me.
Last edit: kk_huk 2016-06-20
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 following in this article to be able adap the default acoustic model. I am on "Creating transformation with MLLR" step.
However when I run the these code blocks :
It gives an error.
Before I have looked for about this error in this forum. But I couldn't find any similar issue.
I hope that anyone can help me.
Last edit: kk_huk 2016-06-20
You still confused en-us continuous model with en-us-ptm ptm model. Make sure you use a model consistently.
Oops my bad :/ I had tought that I changed the model with write one. But I have changed with wrong one again. I guess, I need some coffee.
Thanks alot. Nickolay
Last edit: kk_huk 2016-06-21