[hts-users:01320] problem in using hts_engine
- Subject: [hts-users:01320] problem in using hts_engine
- From: bereket kasaye <bereket_k@xxxxxxxxx>
- Date: Thu, 10 Apr 2008 08:14:17 -0700 (PDT)
- Delivered-to: hts-users@xxxxxxxxxxxxxxx
- Domainkey-signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=X-YMail-OSG:Received:Date:From:Subject:To:MIME-Version:Content-Type:Content-Transfer-Encoding:Message-ID; b=IsR+Y1zg87xXm9iJ9iJTwOqSkre8y66bQBbZu4HSkoSg/grbUFxcyRRCO4iFYlNsmE6FzqoUpUpiLbqcJ0oMFz7eudRGUT5EY28SgtzqlMAwN+hEQcBkjiBjPP3vziFeODBlLpiBIZfSK1RzTxZgWiNL1IcLGalYwdYXm6WzsDA=;
Hi,
I used the hts, prepared for festival and the .lab file from HTS-demo, to get the synthesized speech. And I used the options as follows, but it generates an error.
bereket@bereket-desktop:~/Desktop/Experiment/hts$ hts_engine -td trees-dur.inf -tf trees-lf0.inf -tm trees-mcep.inf -md duration.pdf -mf lf0.pdf -mm mcep.pdf -df lf0_dyn.win -dm mcep_dyn.win -od duration -of frequency -om mel_cep -or raw -ow wave -ot trace alice01.lab
Error: HTS_HTS_ModelSet_load: #duration pdf must be positive value.
How do I fix this problem.
My second question is, How do i generate .inf, .pdf and mcc files to my own voices. HTK generates only mfcc's.
Thank you in advance.
bereke __________________________________________________
Do You Yahoo!?
Tired of spam? Yahoo! Mail has the best spam protection around
http://mail.yahoo.com
- Follow-Ups
-
- [hts-users:01321] Re: problem in using hts_engine, Simon King