Hello all, I've just backported hts_engine from HTS-2.0 to festival engine: http://nshmyrev.narod.ru/temp/hts-festival-2.0.tar.gz You have to replace hts_engine directory in festival, replace awb_hts.scm file in voice dir toto take new .win files and put win file into voice/hts dir as usual. After that festival will work and synthetise prompts with old pdfs and new engine. I didn't touch mlsa, so clustergen voices will use old vocoder. I also didn't experimented with new options yet, like postfilter, although it should be easier to try them now. Hope, it will be useful.
Attachment:
signature.asc
Description: =?koi8-r?q?=FC=D4=C1?==?koi8-r?q?_=DE=C1=D3=D4=D8?= =?koi8-r?q?_=D3=CF=CF=C2=DD=C5=CE=C9=D1?= =?koi8-r?q?_=D0=CF=C4=D0=C9=D3=C1=CE=C1?= =?koi8-r?q?_=C3=C9=C6=D2=CF=D7=CF=CA?= =?koi8-r?q?_=D0=CF=C4=D0=C9=D3=D8=C0?=