{"id":103762,"date":"2022-04-11T15:36:48","date_gmt":"2022-04-11T13:36:48","guid":{"rendered":"https:\/\/prohoster.info\/blog\/novosti-interneta\/vypusk-sintezatora-rechi-rhvoice-1-8-0"},"modified":"2022-04-11T15:36:48","modified_gmt":"2022-04-11T13:36:48","slug":"vypusk-sintezatora-rechi-rhvoice-1-8-0","status":"publish","type":"post","link":"https:\/\/prohoster.info\/sq\/blog\/novosti-interneta\/vypusk-sintezatora-rechi-rhvoice-1-8-0","title":{"rendered":"L\u00ebshimi i sintetizuesit t\u00eb t\u00eb folurit RHVoice 1.8.0.","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"
U publikua versioni i sistem\u00ebs s\u00eb hapur t\u00eb sintetik\u00ebs s\u00eb z\u00ebrit RHVoice 1.8.0, e cila fillimisht u zhvillua p\u00ebr t\u00eb siguruar mb\u00ebshtetje cil\u00ebsore p\u00ebr gjuh\u00ebn ruse, por m\u00eb pas u adaptua edhe p\u00ebr gjuh\u00eb t\u00eb tjera, p\u00ebrfshir\u00eb anglishten, portugezen, ukrainishten, kirgizishten, tatarishten dhe gjeorgjishten. Kodi \u00ebsht\u00eb shkruar n\u00eb C++ dhe shp\u00ebrndahet n\u00ebn licenc\u00ebn LGPL 2.1. Mb\u00ebshtetet funksionimi n\u00eb GNU\/Linux, Windows dhe Android. Programi \u00ebsht\u00eb i pajtuesh\u00ebm me nd\u00ebrfaqet standarde TTS (text-to-speech) p\u00ebr konvertimin e tekstit n\u00eb t\u00eb folur: SAPI5 (Windows), Speech Dispatcher (GNU\/Linux) dhe Android Text-To-Speech API, por gjithashtu mund t\u00eb p\u00ebrdoret n\u00eb lexuesin e ekranit NVDA. Krijuesja dhe zhvilluesja kryesore e RHVoice \u00ebsht\u00eb Olga Yakovleva, e cila vazhdon projektin pavar\u00ebsisht verb\u00ebris\u00eb totale. <\/p>\n
N\u00eb versionin 1.8 p\u00ebr platform\u00ebn Android \u00ebsht\u00eb propozuar nj\u00eb sistem i ri p\u00ebr menaxhimin e t\u00eb dh\u00ebnave t\u00eb z\u00ebrit dhe gjuh\u00ebs, duke lejuar shkarkimin e p\u00ebrdit\u00ebsimeve t\u00eb t\u00eb dh\u00ebnave t\u00eb z\u00ebrit pa p\u00ebrdit\u00ebsuar aplikacionin mobil. Kontrolli p\u00ebr shfaqjen e p\u00ebrdit\u00ebsimeve t\u00eb t\u00eb dh\u00ebnave p\u00ebr z\u00ebrat dhe gjuh\u00ebt e shtuar b\u00ebhet automatikisht. P\u00ebr m\u00eb tep\u00ebr, n\u00eb k\u00ebt\u00eb version t\u00eb ri \u00ebsht\u00eb implementuar mb\u00ebshtetje p\u00ebr gjuh\u00ebn polake dhe \u00ebsht\u00eb shtuar nj\u00eb z\u00eb i ri p\u00ebr gjuh\u00ebn maqedonase. \u00cbsht\u00eb siguruar pajtueshm\u00ebria me versionet e reja alfa dhe beta t\u00eb lexuesit t\u00eb ekranit NVDA. Jan\u00eb eliminuar problemet me nd\u00ebrtimin n\u00eb platform\u00ebn Linux q\u00eb ndodhnin n\u00eb munges\u00eb t\u00eb Speech Dispatcher. <\/p>\n
Kujtojm\u00eb se n\u00eb RHVoice p\u00ebrdoren arritjet e projektit HTS (HMM\/DNN-based Speech Synthesis System) dhe metoda parametrike e sintez\u00ebs me modelet statistikore (Statistical Parametric Synthesis mbi baz\u00ebn e HMM - Hidden Markov Model). Avantazhi i modelit statistik \u00ebsht\u00eb se ka shpenzime t\u00eb ul\u00ebta operacionale dhe nuk k\u00ebrkon shum\u00eb energji nga CPU. T\u00eb gjitha operacionet kryhen lokal n\u00eb sistemin e p\u00ebrdoruesit. Mb\u00ebshteten tre nivele t\u00eb cil\u00ebsis\u00eb s\u00eb z\u00ebrit (sa m\u00eb i ul\u00ebt t\u00eb jet\u00eb niveli i cil\u00ebsis\u00eb - aq m\u00eb e lart\u00eb \u00ebsht\u00eb performanca dhe m\u00eb e shpejt\u00eb \u00ebsht\u00eb koha e reagimit). <\/p>\n
Nj\u00eb nga disavantazhet e modelit statistik \u00ebsht\u00eb cil\u00ebsia e ul\u00ebt e shqiptimit, e cila nuk arrin nivelin e sintetizator\u00ebve q\u00eb gjenerojn\u00eb z\u00eb me kombinim t\u00eb fragmenteve t\u00eb z\u00ebrit natyror. Megjithat\u00eb, rezultati \u00ebsht\u00eb mjaft i qart\u00eb dhe p\u00ebrngjan me transmetimin e nj\u00eb regjistrimi nga nj\u00eb megafon. Si krahasim, projekti Silero, i cili ofron nj\u00eb motor t\u00eb hapur p\u00ebr sintetizimin e z\u00ebrit duke p\u00ebrdorur teknologji t\u00eb m\u00ebsimit t\u00eb makinave dhe nj\u00eb grup modelesh p\u00ebr gjuh\u00ebn ruse, \u00ebsht\u00eb m\u00eb i mir\u00eb se RHVoice n\u00eb cil\u00ebsi. <\/p>\n
P\u00ebr gjuh\u00ebn ruse jan\u00eb t\u00eb disponueshme 14 variante z\u00ebra, p\u00ebr anglishten - 6. Z\u00ebra formohen mbi baz\u00ebn e regjistrimeve t\u00eb t\u00eb folurit natyror. N\u00eb cil\u00ebsime mund t\u00eb ndryshohet shpejt\u00ebsia, lart\u00ebsia dhe volumi. P\u00ebr t\u00eb ndryshuar tempin mund t\u00eb p\u00ebrdoret biblioteka Sonic. \u00cbsht\u00eb e mundur p\u00ebrcaktimi automatik dhe kalimi i gjuh\u00ebs mbi baz\u00ebn e analiz\u00ebs s\u00eb tekstit hyr\u00ebs (p\u00ebr shembull, p\u00ebr fjal\u00ebt dhe citatet n\u00eb nj\u00eb gjuh\u00eb tjet\u00ebr mund t\u00eb p\u00ebrdoret modeli i sintez\u00ebs natyrore p\u00ebr k\u00ebt\u00eb gjuh\u00eb). Mb\u00ebshteten profil\u00ebt e z\u00ebrit q\u00eb p\u00ebrcaktojn\u00eb kombinimet e z\u00ebra p\u00ebr gjuh\u00eb t\u00eb ndryshme. \n Burimi: opennet.ru<\/a> <\/p>","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"excerpt":{"rendered":"