{"id":102522,"date":"2021-12-08T15:37:00","date_gmt":"2021-12-08T13:37:00","guid":{"rendered":"https:\/\/prohoster.info\/blog\/novosti-interneta\/vypusk-sintezatora-rechi-rhvoice-1-6-0"},"modified":"2021-12-08T15:37:00","modified_gmt":"2021-12-08T13:37:00","slug":"vypusk-sintezatora-rechi-rhvoice-1-6-0","status":"publish","type":"post","link":"https:\/\/prohoster.info\/sq\/blog\/news\/vypusk-sintezatora-rechi-rhvoice-1-6-0","title":{"rendered":"Publikimi i sintetizuesit t\u00eb z\u00ebrit RHVoice 1.6.0","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"
Kjo \u00ebsht\u00eb l\u00ebshuar sistemi i hapur i sinthez\u00ebs s\u00eb z\u00ebrit RHVoice 1.6.0, fillimisht i zhvilluar p\u00ebr t\u00eb siguruar mb\u00ebshtetje cil\u00ebsore p\u00ebr gjuh\u00ebn ruse, por pastaj i adaptohet edhe p\u00ebr gjuh\u00eb t\u00eb tjera, p\u00ebrfshir\u00eb anglishten, portugezen, ukrainashten, kirgizishten, tataren dhe gjeorgjianen. Kodi \u00ebsht\u00eb shkruar n\u00eb C++ dhe p\u00ebrhapet n\u00ebn licenc\u00ebn LGPL 2.1. Mb\u00ebshtetet puna n\u00eb GNU\/Linux, Windows dhe Android. Programi \u00ebsht\u00eb i pajtuesh\u00ebm me nd\u00ebrfaqet tipike TTS (text-to-speech) p\u00ebr transformimin e tekstit n\u00eb z\u00eb: 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. Krijuesi dhe zhvilluesi kryesor i RHVoice \u00ebsht\u00eb Olga Yakovleva, e cila e zhvillon projektin pavar\u00ebsisht verb\u00ebris\u00eb s\u00eb plot\u00eb. <\/p>\n
N\u00eb versionin e ri jan\u00eb shtuar 5 variante t\u00eb reja z\u00ebrash p\u00ebr gjuh\u00ebn ruse. \u00cbsht\u00eb realizuar mb\u00ebshtetje p\u00ebr gjuh\u00ebn shqipe. Kushtezimi i fjalorit p\u00ebr gjuh\u00ebn ukrainase \u00ebsht\u00eb p\u00ebrmir\u00ebsuar. Mb\u00ebshtetje e zgjeruar p\u00ebr z\u00ebdh\u00ebnien e simboleve emoji. \u00cbsht\u00eb punuar p\u00ebr t\u00eb eliminuar defektet n\u00eb aplikacionin p\u00ebr platform\u00ebn Android, \u00ebsht\u00eb thjeshtuar importimi i fjalor\u00ebve t\u00eb p\u00ebrdoruesve, si dhe \u00ebsht\u00eb shtuar mb\u00ebshtetje p\u00ebr platform\u00ebn Android 11. N\u00eb b\u00ebrtham\u00ebn e motorit jan\u00eb shtuar cil\u00ebsime dhe funksionalitete t\u00eb reja, duke p\u00ebrfshir\u00eb g2p.case, word_break dhe mb\u00ebshtetje p\u00ebr filtrin e ekualizimit. <\/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 n\u00eb dispozicion 13 variante z\u00ebrash, nd\u00ebrsa p\u00ebr gjuh\u00ebn angleze - 5. Z\u00ebrat formohen n\u00eb baza t\u00eb regjistrimeve t\u00eb fjal\u00ebs s\u00eb natyrshme. N\u00eb cil\u00ebsime, mund t\u00eb ndryshoni shpejt\u00ebsin\u00eb, lart\u00ebsin\u00eb dhe z\u00ebrit. P\u00ebr ndryshimin e ritmit, mund t\u00eb p\u00ebrdoret biblioteka Sonic. \u00cbsht\u00eb e mundur automatikisht t\u00eb p\u00ebrcaktohet dhe t\u00eb kaloj\u00eb gjuha 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 at\u00eb gjuh\u00eb). Mb\u00ebshteten profilet e z\u00ebrit, q\u00eb p\u00ebrcaktojn\u00eb kombinimet e z\u00ebrave p\u00ebr gjuh\u00eb t\u00eb ndryshme. \n Burimi: opennet.ru<\/a> <\/p>","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"excerpt":{"rendered":"