{"id":105165,"date":"2022-09-25T21:36:38","date_gmt":"2022-09-25T19:36:39","guid":{"rendered":"https:\/\/prohoster.info\/blog\/novosti-interneta\/otkryt-kod-sistemy-raspoznavaniya-i-perevoda-rechi-whisper"},"modified":"2022-09-25T21:36:38","modified_gmt":"2022-09-25T19:36:39","slug":"otkryt-kod-sistemy-raspoznavaniya-i-perevoda-rechi-whisper","status":"publish","type":"post","link":"https:\/\/prohoster.info\/sk\/blog\/news\/otkryt-kod-sistemy-raspoznavaniya-i-perevoda-rechi-whisper","title":{"rendered":"Otv\u00e1ra sa k\u00f3d syst\u00e9mu rozpozn\u00e1vania a prekladu re\u010di Whisper","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"

Projekt OpenAI, zameran na v\u00fdvoj verejn\u00fdch projektov v oblasti umelej inteligencie, zverejnil v\u00fdsledky t\u00fdkaj\u00face sa syst\u00e9mu rozpozn\u00e1vania re\u010di Whisper. Tvrd\u00ed sa, \u017ee syst\u00e9m pre anglick\u00fd jazyk dosahuje \u00farovne spo\u013eahlivosti a presnosti automatick\u00e9ho rozpozn\u00e1vania bl\u00edzke rozpozn\u00e1vaniu \u010dlovekom. K\u00f3d referen\u010dnej implement\u00e1cie je otvoren\u00fd na b\u00e1ze r\u00e1mca PyTorch a s\u00fa k dispoz\u00edcii u\u017e vycvi\u010den\u00e9 modely pripraven\u00e9 na pou\u017eitie. K\u00f3d je spr\u00edstupnen\u00fd pod licenciou MIT. <\/p>\n

Na \u0161kolenie modelu bolo pou\u017eit\u00fdch 680 tis\u00edc hod\u00edn re\u010dov\u00fdch d\u00e1t, zozbieran\u00fdch z viacer\u00fdch kolekci\u00ed, pokr\u00fdvaj\u00facich r\u00f4zne jazyky a tematick\u00e9 oblasti. Pribli\u017ene 1\/3 pou\u017eit\u00fdch re\u010dov\u00fdch d\u00e1t po\u010das \u0161kolenia poch\u00e1dza z jazykov odli\u0161n\u00fdch od angli\u010dtiny. Navrhnut\u00fd syst\u00e9m spr\u00e1vne spracov\u00e1va situ\u00e1cie ako pr\u00edzvuk, pr\u00edtomnos\u0165 pozadia hluku a pou\u017eitie technick\u00e9ho \u017earg\u00f3nu. Okrem prepisu re\u010di do textu, syst\u00e9m dok\u00e1\u017ee tie\u017e preklada\u0165 re\u010d z \u013eubovo\u013en\u00e9ho jazyka do angli\u010dtiny a detegova\u0165 pr\u00edtomnos\u0165 re\u010di v zvukovom toku. <\/p>\n

Modely s\u00fa vytvoren\u00e9 vo dvoch reprezent\u00e1ci\u00e1ch: model pre anglick\u00fd jazyk a viacjazy\u010dn\u00fd model, ktor\u00fd podporuje vr\u00e1tane ru\u0161tiny, ukrajin\u010diny a bieloru\u0161tiny. Ka\u017ed\u00e1 reprezent\u00e1cia sa \u010falej del\u00ed na 5 vari\u00e1nt, ktor\u00e9 sa odli\u0161uj\u00fa ve\u013ekos\u0165ou a po\u010dtom parametrov pokryt\u00fdch v modeli. \u010c\u00edm v\u00e4\u010d\u0161ia je ve\u013ekos\u0165, t\u00fdm vy\u0161\u0161ia je presnos\u0165 a kvalita rozpozn\u00e1vania, ale aj vy\u0161\u0161ie n\u00e1roky na ve\u013ekos\u0165 videopam\u00e4te GPU a ni\u017e\u0161\u00ed v\u00fdkon. Napr\u00edklad minim\u00e1lna varianta obsahuje 39 mili\u00f3nov parametrov a vy\u017eaduje 1 GB videopam\u00e4te, zatia\u013e \u010do maxim\u00e1lna obsahuje 1550 mili\u00f3nov parametrov a vy\u017eaduje 10 GB videopam\u00e4te. Minim\u00e1lna varianta je r\u00fdchlej\u0161ia ne\u017e maxim\u00e1lna 32-kr\u00e1t.

\"Otv\u00e1ra<\/center> <\/p>\n

Syst\u00e9m vyu\u017e\u00edva architekt\u00faru neur\u00f3novej siete \u201eTransformer\u201c, ktor\u00e1 zah\u0155\u0148a vz\u00e1jomne prepojen\u00e9 enkod\u00e9r a dekod\u00e9r. Zvuk sa rozdel\u00ed na 30-sekundov\u00e9 \u00faryvky, ktor\u00e9 sa preved\u00fa na log-Mel-spektrum a odosielaj\u00fa sa do enkod\u00e9ra. V\u00fdsledok pr\u00e1ce enkod\u00e9ra sa posiela do dekod\u00e9ra, ktor\u00fd predpoved\u00e1 textov\u00fa reprezent\u00e1ciu zmie\u0161an\u00fa so \u0161peci\u00e1lnymi tokenmi, ktor\u00e9 umo\u017e\u0148uj\u00fa v jednej spolo\u010dnej modeli rie\u0161i\u0165 \u00falohy ako ur\u010denie jazyka, zoh\u013eadnenie chronol\u00f3gie v\u00fdslovnosti fr\u00e1z, prepis re\u010di v r\u00f4znych jazykoch a preklad do angli\u010dtiny.
\n
Zdroj: opennet.ru<\/a> <\/p>","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"excerpt":{"rendered":"

\u041f\u0440\u043e\u0435\u043a\u0442 OpenAI, \u0437\u0430\u043d\u0438\u043c\u0430\u044e\u0449\u0438\u0439\u0441\u044f \u0440\u0430\u0437\u0432\u0438\u0442\u0438\u0435\u043c \u043e\u0431\u0449\u0435\u0434\u043e\u0441\u0442\u0443\u043f\u043d\u044b\u0445 \u043f\u0440\u043e\u0435\u043a\u0442\u043e\u0432 \u0432 \u043e\u0431\u043b\u0430\u0441\u0442\u0438 \u0438\u0441\u043a\u0443\u0441\u0441\u0442\u0432\u0435\u043d\u043d\u043e\u0433\u043e \u0438\u043d\u0442\u0435\u043b\u043b\u0435\u043a\u0442\u0430, \u043e\u043f\u0443\u0431\u043b\u0438\u043a\u043e\u0432\u0430\u043b \u043d\u0430\u0440\u0430\u0431\u043e\u0442\u043a\u0438, \u0441\u0432\u044f\u0437\u0430\u043d\u043d\u044b\u0435 \u0441 \u0441\u0438\u0441\u0442\u0435\u043c\u043e\u0439 \u0440\u0430\u0441\u043f\u043e\u0437\u043d\u0430\u0432\u0430\u043d\u0438\u044f \u0440\u0435\u0447\u0438 Whisper. \u0423\u0442\u0432\u0435\u0440\u0436\u0434\u0430\u0435\u0442\u0441\u044f, \u0447\u0442\u043e \u0434\u043b\u044f \u0440\u0435\u0447\u0438 \u043d\u0430 \u0430\u043d\u0433\u043b\u0438\u0439\u0441\u043a\u043e\u043c \u044f\u0437\u044b\u043a\u0435 \u0441\u0438\u0441\u0442\u0435\u043c\u0430 \u043e\u0431\u0435\u0441\u043f\u0435\u0447\u0438\u0432\u0430\u0435\u0442 \u0443\u0440\u043e\u0432\u043d\u0438 \u043d\u0430\u0434\u0451\u0436\u043d\u043e\u0441\u0442\u0438 \u0438 \u0442\u043e\u0447\u043d\u043e\u0441\u0442\u0438 \u0430\u0432\u0442\u043e\u043c\u0430\u0442\u0438\u0447\u0435\u0441\u043a\u043e\u0433\u043e \u0440\u0430\u0441\u043f\u043e\u0437\u043d\u0430\u0432\u0430\u043d\u0438\u044f \u0431\u043b\u0438\u0437\u043a\u0438\u0435 \u043a \u0440\u0430\u0441\u043f\u043e\u0437\u043d\u0430\u0432\u0430\u043d\u0438\u044e \u0447\u0435\u043b\u043e\u0432\u0435\u043a\u043e\u043c. \u041e\u0442\u043a\u0440\u044b\u0442\u044b \u043a\u043e\u0434 \u044d\u0442\u0430\u043b\u043e\u043d\u043d\u043e\u0439 \u0440\u0435\u0430\u043b\u0438\u0437\u0430\u0446\u0438\u0438 \u043d\u0430 \u0431\u0430\u0437\u0435 \u0444\u0440\u0435\u0439\u043c\u0432\u043e\u0440\u043a\u0430 PyTorch \u0438 \u043d\u0430\u0431\u043e\u0440 \u0443\u0436\u0435 \u043e\u0431\u0443\u0447\u0435\u043d\u043d\u044b\u0445 \u043c\u043e\u0434\u0435\u043b\u0435\u0439, \u0433\u043e\u0442\u043e\u0432\u044b\u0445 \u0434\u043b\u044f \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043d\u0438\u044f. \u041a\u043e\u0434 \u043e\u0442\u043a\u0440\u044b\u0442 […]<\/p>\n","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"author":1,"featured_media":105166,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[702],"tags":[],"class_list":["post-105165","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news"],"aioseo_notices":[],"aioseo_head":"\n\t\t\n\t\n\t\n\t\n\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\n","aioseo_head_json":{"title":"\ud83e\udd47Otvorte k\u00f3d syst\u00e9mu rozpozn\u00e1vania a prekladu re\u010di Whisper | ProHoster","description":"Projekt OpenAI, ktor\u00fd sa zaober\u00e1 rozvojom verejn\u00fdch projektov v oblasti umelej inteligencie, zverejnil v\u00fdsledky s\u00favisiace so syst\u00e9mom rozpozn\u00e1vania re\u010di Whisper.","canonical_url":"https:\/\/prohoster.info\/sk\/blog\/news\/otkryt-kod-sistemy-raspoznavaniya-i-perevoda-rechi-whisper","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":""},"schema":null,"og:locale":"sk_SK","og:site_name":"ProHoster | \u041a\u0443\u043f\u0438\u0442\u044c \u043d\u0430\u0434\u0435\u0436\u043d\u044b\u0439 \u0445\u043e\u0441\u0442\u0438\u043d\u0433 \u0434\u043b\u044f \u0441\u0430\u0439\u0442\u043e\u0432 \u0441 \u0437\u0430\u0449\u0438\u0442\u043e\u0439 \u043e\u0442 DDoS, VPS VDS \u0441\u0435\u0440\u0432\u0435\u0440\u044b","og:type":"article","og:title":"\ud83e\udd47\u041e\u0442\u043a\u0440\u044b\u0442 \u043a\u043e\u0434 \u0441\u0438\u0441\u0442\u0435\u043c\u044b \u0440\u0430\u0441\u043f\u043e\u0437\u043d\u0430\u0432\u0430\u043d\u0438\u044f \u0438 \u043f\u0435\u0440\u0435\u0432\u043e\u0434\u0430 \u0440\u0435\u0447\u0438 Whisper | ProHoster","og:description":"\u041f\u0440\u043e\u0435\u043a\u0442 OpenAI, \u0437\u0430\u043d\u0438\u043c\u0430\u044e\u0449\u0438\u0439\u0441\u044f \u0440\u0430\u0437\u0432\u0438\u0442\u0438\u0435\u043c \u043e\u0431\u0449\u0435\u0434\u043e\u0441\u0442\u0443\u043f\u043d\u044b\u0445 \u043f\u0440\u043e\u0435\u043a\u0442\u043e\u0432 \u0432 \u043e\u0431\u043b\u0430\u0441\u0442\u0438 \u0438\u0441\u043a\u0443\u0441\u0441\u0442\u0432\u0435\u043d\u043d\u043e\u0433\u043e \u0438\u043d\u0442\u0435\u043b\u043b\u0435\u043a\u0442\u0430, \u043e\u043f\u0443\u0431\u043b\u0438\u043a\u043e\u0432\u0430\u043b \u043d\u0430\u0440\u0430\u0431\u043e\u0442\u043a\u0438, \u0441\u0432\u044f\u0437\u0430\u043d\u043d\u044b\u0435 \u0441 \u0441\u0438\u0441\u0442\u0435\u043c\u043e\u0439 \u0440\u0430\u0441\u043f\u043e\u0437\u043d\u0430\u0432\u0430\u043d\u0438\u044f \u0440\u0435\u0447\u0438 Whisper.","og:url":"https:\/\/prohoster.info\/sk\/blog\/news\/otkryt-kod-sistemy-raspoznavaniya-i-perevoda-rechi-whisper","og:image":"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg","og:image:secure_url":"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg","og:image:width":350,"og:image:height":350,"article:published_time":"2022-09-25T19:36:39+00:00","article:modified_time":"2022-09-25T19:36:39+00:00","article:publisher":"https:\/\/www.facebook.com\/prohoster","article:author":"https:\/\/www.facebook.com\/prohoster"},"aioseo_meta_data":[],"gt_translate_keys":[{"key":"link","format":"url"}],"_links":{"self":[{"href":"https:\/\/prohoster.info\/sk\/wp-json\/wp\/v2\/posts\/105165","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/prohoster.info\/sk\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/prohoster.info\/sk\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/prohoster.info\/sk\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/prohoster.info\/sk\/wp-json\/wp\/v2\/comments?post=105165"}],"version-history":[{"count":0,"href":"https:\/\/prohoster.info\/sk\/wp-json\/wp\/v2\/posts\/105165\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/prohoster.info\/sk\/wp-json\/wp\/v2\/media\/105166"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/sk\/wp-json\/wp\/v2\/media?parent=105165"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/sk\/wp-json\/wp\/v2\/categories?post=105165"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/sk\/wp-json\/wp\/v2\/tags?post=105165"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}