[hts-users:04114] Re:

[Keiichiro Oura <uratec@xxxxxxxxxxxxxxx>]

Hi,

After generation labels are added, lists should be re-created.

% cd data;
% make list scp

Regards,
Keiichiro Oura




2014-09-04 15:14 GMT+09:00 Sumalatha Emmela <latha.emmela@xxxxxxxxx>:
> Hi,
>       I have already generated labels and stored in data/labels/gen. I have
> also run Training.pl. But the problem is I am not getting how to generate
> voice for a given text.
>
>
> On Wed, Sep 3, 2014 at 4:56 PM, Marc Evrard <marc.evrard@xxxxxxxxx> wrote:
>>
>> The perl training script provided in the Demo includes the synthesis
>> procedure through HTS. You could first try using it.
>> You need to generate the labels to synthesis and store them in lab files
>> under data/labels/gen.
>> Then select the 4 steps below in the config file (if you stick to single
>> mixtures) and run Training.pl.
>>
>> $MKUNG = 1; # making unseen models (GV)
>> $MKUN1 = 1; # making unseen models (1mix)
>> $PGEN1 = 1; # generating speech parameter sequences (1mix)
>> $WGEN1 = 1; # synthesizing waveforms (1mix)
>>
>>
>> On Wed, Sep 3, 2014 at 7:38 AM, Sumalatha Emmela <latha.emmela@xxxxxxxxx>
>> wrote:
>>>
>>>
>>> Hi,
>>>      I trained HTS with STRAIGHTV40. I am not getting any idea how to
>>> proceed further. Please give the procedure how to synthesize the text.
>>
>>
>
>
>
> --
> Sumalatha
> M.Tech (CESP)
> Bapatla Engineering College
> Bapatla