[hts-users:00102] : Re: HTS-demo error
- Subject: [hts-users:00102] : Re: HTS-demo error
- From: "Maider Lehr" <mlehr@xxxxxxxxxxxx>
- Date: Mon, 9 May 2005 09:33:22 +0200
- Importance: Normal
Hi,
And what do I check using HList? I have done it and I have obtained a list
of numbers but I don't know what is their meaning.
Best Regards,
Maider
-----Mensaje original-----
De: Heiga Zen (Byung-Ha Chun) [mailto:zen@xxxxxxxxxxxxxxxx]
Enviado el: martes, 26 de abril de 2005 14:53
Para: hts-users@xxxxxxxxxxxxxxxxxxxxxxxxx
Asunto: [hts-users:00098] Re: HTS-demo error
Hi,
Maider Lehr wrote:
> Hello,
> I have installed HTS -demo, but when I have tested it I have had some
> problems.
> The fact is that when I run the training script to test the intallation:
> perl scripts/Training_cmu_us_arctic_awb.pl
>
> I get the following error:
>
> =============== aa ================
> /usr/local/bin/HInit -A -C
> /home/h21/Festival/HTS-demo/configs/default.conf -D -T 1 -m 1 -v 1.0e-04
> -I /home/h21/Festival/HTS-demo_CMU-ARCTIC-AWB/labels/mono_awb.mlf -M
> /home/h21/Festival/HTS-demo/hmms/cmu_us_arctic/awb/cmp/HInit -S
>
/home/h21/Festival/HTS-demo_CMU-ARCTIC-AWB/lists/data_cmu_us_arctic_awb.scp
-l aa -o aa /home/h21/Festival/HTS-demo/proto/s5_m1_c75_p3.prt
>
> HTK Configuration Parameters[5]
> Module/Tool Parameter Value
> # NATURALWRITEORDER TRUE
> # NATURALREADORDER TRUE
> # DVFLOORSCALE 0.010000
> # APPLYVFLOOR TRUE
> # TREEMERGE FALSE
>
> Initialising HMM /home/h21/Festival/HTS-demo/proto/s5_m1_c75_p3.prt . .
> .
> States : 2 3 4 5 6 (width)
> Mixes s1: 1 1 1 1 1 ( 75 )
> ( 75 )
> Num Using: 0 0 0 0 0
> Mixes s2: 2 2 2 2 2 ( 1 )
> ( MSD <= 1 )
> Num Using: 0 0 0 0 0
> Mixes s3: 2 2 2 2 2 ( 1 )
> ( MSD <= 1 )
> Num Using: 0 0 0 0 0
> Mixes s4: 2 2 2 2 2 ( 1 )
> ( MSD <= 1 )
> Num Using: 0 0 0 0 0
> Parm Kind: USER
> Number of owners = 1
> SegLab : aa
> maxIter : 20
> epsilon : 0.000100
> minSeg : 1
> Updating : Means Variances MixWeights/DProbs TransProbs
>
> - system is PLAIN
> 809 Observation Sequences Loaded
> Starting Estimation Process
> ERROR [+2126] ViterbiAlign: No path found in 1'th segment
> FATAL ERROR - Terminating program /usr/local/bin/HInit
> ==================================================
> Realtime 0: 0.33
> ==================================================
> Error in this command : /usr/local/bin/HInit -A -C
> /home/h21/Festival/HTS-demo/configs/default.conf -D -T 1 -m 1 -v 1.0e-04
> -I /home/h21/Festival/HTS-demo_CMU-ARCTIC-AWB/labels/mono_awb.mlf -M
> /home/h21/Festival/HTS-demo/hmms/cmu_us_arctic/awb/cmp/HInit -S
>
/home/h21/Festival/HTS-demo_CMU-ARCTIC-AWB/lists/data_cmu_us_arctic_awb.scp
-l aa -o aa /home/h21/Festival/HTS-demo/proto/s5_m1_c75_p3.prt
Maybe your data are broken.
Please check then using HList.
/usr/local/bin/HList -C \
/home/h21/Festival/HTS-demo_CMU-ARCTIC-AWB/hlist.conf \
/home/h21/Festival/HTS-demo_CMU-ARCTIC-AWB/cmp/cmu_us_arctic_awb_a0001.cmp
Regards,
Heiga Zen
--
------------------------------------------------
Heiga Zen (in Japanese pronunciation)
Byung-Ha Chun (in Korean pronunciation)
Department of Computer Science and Engineering
Graduate School of Engineering
Nagoya Institute of Technology
Japan
e-mail: zen@xxxxxxxxxxxxxxxx
web: http://kt-lab.ics.nitech.ac.jp/~zen
------------------------------------------------
- Follow-Ups
-
- [hts-users:00103] Re: : Re: HTS-demo error, Heiga Zen (Byung-Ha Chun)