[hts-users:03791] Re: Issue in joining models after reclustering

[Keiichiro Oura <uratec@xxxxxxxxxxxxxxx>]

Hi,

It seems mismatch between model file (*.mmf) and tree file (*.inf).
Please, check file names carefully.
(If you use HTS demo scripts, re-clustered model file is
"model/qst001/ver1/re_clustered.mmf" and re-clustered tree file is
"trees/qst001/ver1/hnr.inf.untied".)

Regards,
Keiichiro Oura




2013/6/11 Pierre-Edouard Honnet <pe.honnet@xxxxxxxxx>:
> Hi,
>
> I used some scripts to build models with regular STRAIGHT features and got
> no problem. I would like to try these scripts with other features, however I
> adapted the scripts and during the training got some warnings in joining
> models and untying steps, and that causes an error in synthesis and in this
> command:
>
> Error in this command : /idiap/home/xna/HTS/tools/HTS-2.2/bin/HHEd -A -B -C
> config/general.conf -T 1 -D -V -H hmm/clustered.cmp.mmf -i -p
> hmm/hts_engine/chs.hnr.hed hmm/context.cmp.list
>
> The warnings I got are of the form:
>
> /idiap/home/xna/HTS/tools/HTS-2.2/bin/HHEd -A -B -C config/general.conf -T 1
> -D -V -H hmm/clustered.cmp.mmf -i -p hmm/hts_engine/chs.hnr.hed
> hmm/context.cmp.list
>
> HTK Configuration Parameters[7]
>   Module/Tool     Parameter                  Value
> #                 MAXSTDDEVCOEF                 10
> #                 DURVARFLOORPERCENTILE          1.000000
> #                 APPLYDURVARFLOOR              TRUE
> #                 VFLOORSCALESTR  Vector 4 0.01 0.01 0.01 0.01
> #                 APPLYVFLOOR                 TRUE
> #                 NATURALWRITEORDER              TRUE
> #                 NATURALREADORDER              TRUE
>
>
> HTK Version Information
> Module     Version    Who    Date      : CVS Info
> HHEd       3.4.1      CUED   12/03/09  : $Id: HHEd.c,v 1.105 2011/06/16
> 05:18:47 uratec Exp $
> HShell     3.4.1      CUED   12/03/09  : $Id: HShell.c,v 1.15 2011/06/16
> 04:18:29 uratec Exp $
> HMem       3.4.1      CUED   12/03/09  : $Id: HMem.c,v 1.11 2011/06/16
> 04:18:29 uratec Exp $
> HLabel     3.4.1      CUED   12/03/09  : $Id: HLabel.c,v 1.12 2011/06/16
> 04:18:29 uratec Exp $
> HMath      3.4.1      CUED   12/03/09  : $Id: HMath.c,v 1.15 2011/06/16
> 04:18:29 uratec Exp $
> HSigP      3.4.1      CUED   12/03/09  : $Id: HSigP.c,v 1.8 2011/06/16
> 04:18:29 uratec Exp $
> HWave      3.4.1      CUED   12/03/09  : $Id: HWave.c,v 1.11 2011/06/16
> 04:18:29 uratec Exp $
> HAudio     3.4.1      CUED   12/03/09  : $Id: HAudio.c,v 1.9 2011/06/16
> 04:18:28 uratec Exp $
> HVQ        3.4.1      CUED   12/03/09  : $Id: HVQ.c,v 1.8 2011/06/16
> 04:18:29 uratec Exp $
> HModel     3.4.1      CUED   12/03/09  : $Id: HModel.c,v 1.42 2011/06/16
> 05:07:56 bonanza Exp $
> HParm      3.4.1      CUED   12/03/09  : $Id: HParm.c,v 1.15 2011/06/16
> 04:18:29 uratec Exp $
> HUtil      3.4.1      CUED   12/03/09  : $Id: HUtil.c,v 1.31 2011/06/16
> 04:18:29 uratec Exp $
> HAdapt     3.4.1      CUED   12/03/09  : $Id: HAdapt.c,v 1.64 2011/06/16
> 04:15:50 uratec Exp $
>
> HHEd
>  30119/29935 Models Loaded [7 states max, 1 mixes max]
>
> TR 2
>  Adjusting trace level
>
> LT hmm/tree.hnr.inf
>  Loading questions/trees from file
>  WARNING [-2661]  LoadTree: Macro hnr_s2_17 not recognised in
> /idiap/home/xna/HTS/tools/HTS-2.2/bin/HHEd
>  WARNING [-2661]  LoadTree: Macro hnr_s2_19 not recognised in
> /idiap/home/xna/HTS/tools/HTS-2.2/bin/HHEd
>
> This happens only for the new feature, however the commands used are the
> same with other features. Some of the hnr_sx_xx exist in
> hmm/clustered.cmp.mmf, but a lot of them are missing.
>
> I found this post
> http://hts.sp.nitech.ac.jp/hts-users/spool/2011/msg00411.html mentioning the
> same problem, however I checked and the last reclustered tree file is used.
>
> Would you have an idea of what is wrong?
>
> Thanks and regards,
> Pierre-Edouard Honnet