{"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\/news\/vypusk-sintezatora-rechi-rhvoice-1-8-0","title":{"rendered":"L\u00ebshimi i sintetik\u00ebs s\u00eb z\u00ebrit RHVoice 1.8.0","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"
L\u00ebshimi i versionit t\u00eb hapur t\u00eb sistemit t\u00eb sintez\u00ebs s\u00eb z\u00ebrit RHVoice 1.8.0, i cili fillimisht u zhvillua p\u00ebr t\u00eb ofruar mb\u00ebshtetje cil\u00ebsore p\u00ebr gjuh\u00ebn ruse, por m\u00eb pas u adaptua edhe p\u00ebr gjuh\u00eb t\u00eb tjera, duke p\u00ebrfshir\u00eb anglishten, portugezishten, ukrainishten, kirgize, tatarishten dhe gjeorgjianishten. 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 p\u00ebrputhsh\u00ebm me nd\u00ebrfaqet standarde TTS (text-to-speech) p\u00ebr konvertimin e tekstit n\u00eb folje: SAPI5 (Windows), Speech Dispatcher (GNU\/Linux) dhe Android Text-To-Speech API, por gjithashtu mund t\u00eb p\u00ebrdoret n\u00eb leximin e ekranit NVDA. Krijuesi dhe zhvilluesi kryesor i RHVoice \u00ebsht\u00eb Olga Yakovleva, e cila zhvillon projektin pavar\u00ebsisht verb\u00ebris\u00eb s\u00eb saj t\u00eb plot\u00eb. <\/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\u00ebve, q\u00eb lejon shkarkimin e azhurnimeve t\u00eb t\u00eb dh\u00ebnave t\u00eb z\u00ebrit pa e rinovuar aplikacionin mobil. Kontrolli i shfaqjes s\u00eb azhurnimeve t\u00eb t\u00eb dh\u00ebnave p\u00ebr z\u00ebra dhe gjuh\u00eb t\u00eb shtuar b\u00ebhet automatikisht. P\u00ebr m\u00eb tep\u00ebr, n\u00eb k\u00ebt\u00eb l\u00ebshim t\u00eb ri \u00ebsht\u00eb realizuar mb\u00ebshtetje p\u00ebr gjuh\u00ebn polake dhe \u00ebsht\u00eb shtuar nj\u00eb z\u00eb i ri p\u00ebr gjuh\u00ebn maqedonase. \u00cbsht\u00eb garantuar p\u00ebrputhshm\u00ebria me versionet e reja alfa dhe beta t\u00eb lexuesit t\u00eb ekranit NVDA. Jan\u00eb eliminuar problemet e nd\u00ebrtimit n\u00eb platform\u00ebn Linux, t\u00eb cilat ndodhnin n\u00eb munges\u00eb t\u00eb Speech Dispatcher. <\/p>\n
Kumbara se se RHVoice p\u00ebrdoren zhvillimet e projektit HTS (Sistemi i Sintetizimit t\u00eb Z\u00ebrit i Bazuar n\u00eb HMM\/DNN) dhe metoda parametrike e sintetik\u00ebs me modelet statistikore (Sintetizimi Parametrik Statistikor n\u00eb baza HMM - Modeli i Markovit t\u00eb Fshehur). Avantazhi i modelit statistikor \u00ebsht\u00eb kosto e ul\u00ebt dhe k\u00ebrkesa e pak\u00ebt p\u00ebr fuqin\u00eb e CPU. T\u00eb gjitha operacionet kryhen lokal ndaj sistemit t\u00eb p\u00ebrdoruesit. Mb\u00ebshtetet tre nivele t\u00eb cil\u00ebsis\u00eb s\u00eb z\u00ebrit (sa m\u00eb e ul\u00ebt t\u00eb jet\u00eb cil\u00ebsia - aq m\u00eb e lart\u00eb \u00ebsht\u00eb performanca dhe m\u00eb e vog\u00ebl koha e reagimit). <\/p>\n
Disavantazhi i modelit statistik \u00ebsht\u00eb cil\u00ebsia relativisht e ul\u00ebt e shqipimit, e cila nuk arrin nivelin e sintezator\u00ebve q\u00eb gjenerojn\u00eb z\u00eb nga kombinimi i fragmenteve t\u00eb z\u00ebrit natyror, por megjithat\u00eb rezultati \u00ebsht\u00eb mjaft i qart\u00eb dhe ngjan me transmetimin e nj\u00eb regjistrimi me altoparlant. P\u00ebr krahasim, projekti Silero, q\u00eb ofron nj\u00eb motor t\u00eb hapur p\u00ebr sintez\u00ebn e z\u00ebrit mbi baz\u00ebn e teknologjive t\u00eb m\u00ebsimit t\u00eb makinerive dhe nj\u00eb grup modelesh p\u00ebr gjuh\u00ebn ruse, e tejkalon cil\u00ebsin\u00eb e RHVoice. <\/p>\n
P\u00ebr gjuh\u00ebn ruse jan\u00eb t\u00eb disponueshme 14 variacione t\u00eb z\u00ebrit, p\u00ebr anglishten - 6. Z\u00ebrat formohen n\u00eb baz\u00eb t\u00eb regjistrimeve t\u00eb fjal\u00ebs natyrore. N\u00eb cil\u00ebsime mund t\u00eb ndryshoni shpejt\u00ebsin\u00eb, lart\u00ebsin\u00eb dhe volumin. P\u00ebr t\u00eb ndryshuar ritmin mund t\u00eb p\u00ebrdoret biblioteka Sonic. \u00cbsht\u00eb e mundur p\u00ebrcaktimi automatik dhe kalimi i gjuh\u00ebs n\u00eb baz\u00eb t\u00eb 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 sintetik\u00ebs natyror p\u00ebr k\u00ebt\u00eb gjuh\u00eb). Mb\u00ebshteten profillet zanore q\u00eb p\u00ebrcaktojn\u00eb kombinime z\u00ebrash p\u00ebr gjuh\u00eb t\u00eb ndryshme. \n Burimi: opennet.ru<\/a> <\/p>","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"excerpt":{"rendered":"