[Subject Prev][Subject Next][Thread Prev][Thread Next][Date Index][Thread Index]

[hts-users:04479] Re: HTS-2.3.1


I am trying to do speaker adaptation using latest packages .

( have done speaker adaptation with previous release).

What i could observe is SAT is taking more time than previous ( database consist of 5 speakers 1000 waves per speaker).
Earlier with the same data the SAT was completed in 4 days (3+ 18hours) but this time it SAT has not yet completed in four days.

Please help 

The training is running on UBUTU 16.04 

On Mon, Dec 26, 2016 at 4:12 PM, Keiichi Tokuda <tokuda@xxxxxxxxxxxx> wrote:
We are please to inform you the release of

            The HMM-based Speech Synthesis System (HTS)
             version 2.3.1  release December 25, 2016

for HMM-based speech synthesis.  We apologize if you receive multiple
copies.  Please check

 http://hts.sp.nitech.ac.jp/

One of new features is a DNN-based demo script.

We would appreciate it if you would distribute this email to anyone
who would be interested in this software toolkit.

Best regards,
Keiichi Tokuda
in behalf of HTS Working Group
tokuda@xxxxxxxxxxxx
http://www.sp.nitech.ac.jp/~tokuda/