{"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\/ro\/blog\/news\/otkryt-kod-sistemy-raspoznavaniya-i-perevoda-rechi-whisper","title":{"rendered":"S-a deschis codul sistemului de recunoa\u0219tere \u0219i traducere a vorbirii Whisper","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"

Proiectul OpenAI, care se ocup\u0103 de dezvoltarea proiectelor accesibile \u00een domeniul inteligen\u021bei artificiale, a publicat realiz\u0103rile legate de sistemul de recunoa\u0219tere vocal\u0103 Whisper. Se afirm\u0103 c\u0103 pentru vorbirea \u00een limba englez\u0103, sistemul ofer\u0103 niveluri de fiabilitate \u0219i precizie a recunoa\u0219terii automate apropiate de recunoa\u0219terea uman\u0103. Codul pentru implementarea de referin\u021b\u0103 bazat\u0103 pe framework-ul PyTorch \u0219i un set de modele deja antrenate, gata de utilizare, sunt disponibile public. Codul este deschis sub licen\u021ba MIT. <\/p>\n

Pentru antrenarea modelului, au fost utilizate 680.000 de ore de date vocale, adunate din mai multe colec\u021bii, acoperind diferite limbi \u0219i domenii tematice. Aproximativ 1\/3 din datele vocale folosite pentru antrenare provin din limbi diferite de englez\u0103. Sistemul propus proceseaz\u0103 corect situa\u021bii precum pronun\u021bia cu accent, prezen\u021ba zgomotelor de fond \u0219i utilizarea jargonului tehnic. \u00cen plus fa\u021b\u0103 de transcrierea vorbirii \u00een text, sistemul poate, de asemenea, s\u0103 traduc\u0103 vorbirea din orice limb\u0103 \u00een limba englez\u0103 \u0219i s\u0103 detecteze apari\u021bia vorbirii \u00een fluxul audio. <\/p>\n

Modelele sunt create \u00een dou\u0103 reprezent\u0103ri: un model pentru limba englez\u0103 \u0219i un model multilingv, care suport\u0103, printre altele, limbile rom\u00e2n\u0103, ucrainean\u0103 \u0219i belarus\u0103. Fiecare reprezentare este divizat\u0103 \u00een 5 variante, diferite prin dimensiune \u0219i num\u0103rul de parametri acoperi\u021bi \u00een model. Cu c\u00e2t dimensiunea este mai mare, cu at\u00e2t mai mare este precizia \u0219i calitatea recunoa\u0219terii, dar \u0219i cerin\u021bele pentru dimensiunea memoriei video GPU sunt mai mari, iar performan\u021ba este mai redus\u0103. De exemplu, varianta minim\u0103 include 39 de milioane de parametri \u0219i necesit\u0103 1 GB de memorie video, \u00een timp ce varianta maxim\u0103 include 1550 de milioane de parametri \u0219i necesit\u0103 10 GB de memorie video. Varianta minim\u0103 este de 32 de ori mai rapid\u0103 dec\u00e2t cea maxim\u0103.

\"S-a<\/center> <\/p>\n

Sistemul utilizeaz\u0103 arhitectura re\u021belei neuronale \u201eTransformer\u201d, care include un codificator \u0219i un decodificator care interac\u021bioneaz\u0103 \u00eentre ele. Sunetul este \u00eemp\u0103r\u021bit \u00een fragmente de 30 de secunde, care sunt convertite \u00eentr-un spectrogram log-Mel \u0219i trimise codificatorului. Rezultatul muncii codificatorului este direc\u021bionat c\u0103tre decodificator, care prezice o reprezentare textual\u0103, amestecat\u0103 cu tokenuri speciale, permi\u021b\u00e2nd rezolvarea, \u00eentr-un singur model comun, a unor sarcini precum determinarea limbii, considerarea cronologiei pronun\u021b\u0103rii frazelor, transcrierea discursului \u00een diferite limbi \u0219i traducerea \u00een limba englez\u0103.
\n
Sursa: opennet.ro<\/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\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\udd47Codul deschis al sistemului de recunoa\u0219tere \u0219i traducere a vocii Whisper | ProHoster","description":"Proiectul OpenAI, care se ocup\u0103 de dezvoltarea proiectelor publice \u00een domeniul inteligen\u021bei artificiale, a publicat lucr\u0103ri legate de sistemul de recunoa\u0219tere a vocii Whisper.","canonical_url":"https:\/\/prohoster.info\/ro\/blog\/news\/otkryt-kod-sistemy-raspoznavaniya-i-perevoda-rechi-whisper","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":""},"schema":null,"og:locale":"ro_RO","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\/ro\/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\/ro\/wp-json\/wp\/v2\/posts\/105165","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/comments?post=105165"}],"version-history":[{"count":0,"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/posts\/105165\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/media\/105166"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/media?parent=105165"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/categories?post=105165"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/tags?post=105165"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}