{"id":53722,"date":"2019-12-08T00:00:00","date_gmt":"2019-12-07T21:00:00","guid":{"rendered":"https:\/\/prohoster.info\/blog\/blog_prohoster\/kompaniya-mozilla-predstavila-dvizhok-raspoznavaniya-rechi-deepspeech-0-6"},"modified":"2020-02-18T14:01:39","modified_gmt":"2020-02-18T11:01:39","slug":"kompaniya-mozilla-predstavila-dvizhok-raspoznavaniya-rechi-deepspeech-0-6","status":"publish","type":"post","link":"https:\/\/prohoster.info\/ro\/blog\/news\/kompaniya-mozilla-predstavila-dvizhok-raspoznavaniya-rechi-deepspeech-0-6","title":{"rendered":"Compania Mozilla a prezentat motorul de recunoa\u0219tere a vorbirii DeepSpeech 0.6","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"<p><noindex><a rel=\"nofollow\" href=\"https:\/\/hacks.mozilla.org\/2019\/12\/deepspeech-0-6-mozillas-speech-to-text-engine\/\">Prezentat<\/a><\/noindex> lansarea motorului de recunoa\u0219tere vocal\u0103 dezvoltat de compania Mozilla <noindex><a rel=\"nofollow\" href=\"https:\/\/github.com\/mozilla\/DeepSpeech\/releases\/v0.6.0\">DeepSpeech 0.6<\/a><\/noindex>, care implementeaz\u0103 arhitectura de recunoa\u0219tere vocal\u0103 omonim\u0103, <noindex><a rel=\"nofollow\" href=\"https:\/\/arxiv.org\/abs\/1412.5567\">propus\u0103<\/a><\/noindex> de cercet\u0103tori de la compania Baidu. Implementarea este scris\u0103 \u00een limbajul Python, utiliz\u00e2nd platforma de \u00eenv\u0103\u021bare automat\u0103 TensorFlow \u0219i <noindex><a rel=\"nofollow\" href=\"https:\/\/github.com\/mozilla\/DeepSpeech\">se r\u0103sp\u00e2nde\u0219te<\/a><\/noindex> sub licen\u021ba liber\u0103 MPL 2.0. Este compatibil\u0103 cu Linux, Android, macOS \u0219i Windows. Performan\u021ba este suficient\u0103 pentru utilizarea motorului pe pl\u0103ci LePotato, Raspberry Pi 3 \u0219i Raspberry Pi 4.<\/p>\n<p>De asemenea, sunt <noindex><a rel=\"nofollow\" href=\"https:\/\/github.com\/mozilla\/DeepSpeech\/releases\/download\/v0.6.0\/deepspeech-0.6.0-models.tar.gz\">oferite<\/a><\/noindex> modele antrenate, <noindex><a rel=\"nofollow\" href=\"https:\/\/github.com\/mozilla\/DeepSpeech\/releases\/download\/v0.6.0\/audio-0.6.0.tar.gz\">exemple<\/a><\/noindex> de fi\u0219iere audio \u0219i un instrumentar pentru recunoa\u0219tere din linia de comand\u0103. Pentru integrarea func\u021biei de recunoa\u0219tere vocal\u0103 \u00een propriile programe, sunt propuse module gata de utilizat pentru Python, NodeJS, C++ \u0219i .NET (module preg\u0103tite separat de dezvoltatori ter\u021bi pentru <noindex><a rel=\"nofollow\" href=\"https:\/\/github.com\/RustAudio\/deepspeech-rs\">Rust<\/a><\/noindex> \u0219i <noindex><a rel=\"nofollow\" href=\"https:\/\/github.com\/asticode\/go-astideepspeech\">Go<\/a><\/noindex>). Modelul final este disponibil doar pentru limba englez\u0103, dar pentru alte limbi, prin <noindex><a rel=\"nofollow\" href=\"https:\/\/github.com\/mozilla\/DeepSpeech\/wiki#how-can-i-train-using-my-own-data\">documenta\u021bia<\/a><\/noindex> <noindex><a rel=\"nofollow\" href=\"https:\/\/github.com\/mozilla\/DeepSpeech\/blob\/master\/TRAINING.rst#common-voice-training-data\">instruc\u021biuni<\/a><\/noindex> , se poate antrena sistemul \u00een mod autonom, folosind <noindex><a rel=\"nofollow\" href=\"https:\/\/voice.mozilla.org\/en\/datasets\">date vocale<\/a><\/noindex>, colectate de proiectul Common Voice. <\/p>\n<p>DeepSpeech este semnificativ mai simplu dec\u00e2t sistemele tradi\u021bionale \u0219i ofer\u0103 o calitate mai bun\u0103 a recunoa\u0219terii \u00een prezen\u021ba zgomotului exterior. \u00cen dezvoltare nu sunt folosite modele acustice tradi\u021bionale \u0219i concep\u021bia de foneme, ci se aplic\u0103 un sistem de \u00eenv\u0103\u021bare automat\u0103 bine optimizat bazat pe re\u021bele neuronale, care permite evitarea dezvolt\u0103rii de componente separate pentru modelarea diferitelor devia\u021bii, precum zgomotul, ecoul \u0219i caracteristicile vocii. <\/p>\n<p>Partea negativ\u0103 a acestei abord\u0103ri este c\u0103, pentru a ob\u021bine o recunoa\u0219tere de calitate \u0219i a antrena re\u021beaua neuronal\u0103, motorul DeepSpeech necesit\u0103 un volum mare de date diverse, dictate \u00een condi\u021bii reale de diferite voci \u0219i \u00een prezen\u021ba zgomotelor naturale.<br \/>\nColectarea acestor date este efectuat\u0103 de proiectul creat \u00een cadrul Mozilla <noindex><a rel=\"nofollow\" href=\"https:\/\/voice.mozilla.org\/\">Common Voice<\/a><\/noindex>, care ofer\u0103 un set de date verificate cu 780 de ore \u00een <noindex><a rel=\"nofollow\" href=\"https:\/\/voice.mozilla.org\/en\/datasets\">limba englez\u0103<\/a><\/noindex>, 325 \u00een german\u0103, 173 \u00een francez\u0103 \u0219i 27 de ore \u00een rus\u0103. <\/p>\n<p>Scopul final al proiectului Common Voice este acumularea a 10.000 de ore de \u00eenregistr\u0103ri cu diverse pronun\u021bii ale frazelor tipice din discursul uman, ceea ce va permite atingerea unui nivel acceptabil de erori la recunoa\u0219tere. \u00cen forma actual\u0103, participan\u021bii la proiect au dictat deja un total de 4,3 mii de ore, dintre care 3,5 mii au fost verificate. La antrenarea modelului final de limb\u0103 englez\u0103 pentru DeepSpeech au fost utilizate 3816 ore de discurs, \u00een afar\u0103 de Common Voice, care acoper\u0103 date din proiectele LibriSpeech, Fisher \u0219i Switchboard, precum \u0219i incluz\u00e2nd aproximativ 1700 de ore de \u00eenregistr\u0103ri transcrise din emisiuni radio.<\/p>\n<p>Folosind modelul de limb\u0103 englez\u0103 disponibil pentru desc\u0103rcare, nivelul erorilor de recunoa\u0219tere \u00een DeepSpeech este de 7,5% la evaluarea cu un set de teste. <noindex><a rel=\"nofollow\" href=\"http:\/\/www.openslr.org\/12\/\">LibriSpeech<\/a><\/noindex>. Spre compara\u021bie, nivelul erorilor de recunoa\u0219tere uman\u0103 <noindex><a rel=\"nofollow\" href=\"https:\/\/arxiv.org\/pdf\/1412.5567v1.pdf\">este evaluat<\/a><\/noindex> la 5,83%.<\/p>\n<p>DeepSpeech este compus din dou\u0103 subsisteme \u2014 modelul acustic \u0219i decodorul. Modelul acustic utilizeaz\u0103 metode de \u00eenv\u0103\u021bare profund\u0103 pentru a calcula probabilitatea prezen\u021bei anumitor simboluri \u00een sunetul introdus. Decodorul aplic\u0103 un algoritm de c\u0103utare de tip beam pentru a transforma datele despre probabilitatea simbolurilor \u00een reprezentarea textual\u0103.<\/p>\n<p>Principalele <noindex><a rel=\"nofollow\" href=\"https:\/\/github.com\/mozilla\/DeepSpeech\/releases\/v0.6.0\">nout\u0103\u021bi<\/a><\/noindex> DeepSpeech 0.6 (ramura 0.6 nu este compatibil\u0103 cu versiunile anterioare \u0219i necesit\u0103 actualizarea codului \u0219i a modelelor):<\/p>\n<ul>\n<li class=\"l\"> A fost propus un nou decodor \u00een flux, care asigur\u0103 o reac\u021bie mai rapid\u0103 \u0219i nu depinde de dimensiunea datelor audio procesate. Ca rezultat, \u00een noua versiune DeepSpeech s-a reu\u0219it reducerea laten\u021bei la recunoa\u0219tere la 260 ms, ceea ce este cu 73% mai rapid dec\u00e2t \u00eenainte \u0219i permite utilizarea DeepSpeech \u00een solu\u021bii pentru recunoa\u0219terea vocii \u00een timp real.\n<li class=\"l\"> Au fost realizate modific\u0103ri \u00een API \u0219i s-au f\u0103cut lucr\u0103ri pentru unificarea numelui func\u021biilor. Au fost ad\u0103ugate func\u021bii pentru ob\u021binerea de metadate suplimentare despre sincronizare, care permit nu doar ob\u021binerea unui rezultat textual, ci \u0219i urm\u0103rirea leg\u0103turii dintre simboluri \u0219i propozi\u021bii cu pozi\u021bia din fluxul audio.\n<li class=\"l\"> \u00cen instrumentarul pentru antrenarea modulelor a fost ad\u0103ugat\u0103 suport pentru utilizarea bibliotecii <noindex><a rel=\"nofollow\" href=\"https:\/\/developer.nvidia.com\/cudnn\">CuDNN<\/a><\/noindex> pentru optimizarea func\u021bion\u0103rii re\u021belelor neuronale recursive (RNN), ceea ce a permis o cre\u0219tere semnificativ\u0103 (de aproximativ dou\u0103 ori) a performan\u021bei antren\u0103rii modelului, dar a necesitat modific\u0103ri \u00een cod care afecteaz\u0103 compatibilitatea cu modelele preg\u0103tite anterior.\n<li class=\"l\"> Cerine\u021bele minime pentru versiunea TensorFlow au fost ridicate de la 1.13.1 la 1.14.0. A fost ad\u0103ugat\u0103 suportul pentru edi\u021bia u\u0219oar\u0103 TensorFlow Lite, care a redus dimensiunea pachetului DeepSpeech de la 98 MB la 3.7 MB. De asemenea, pentru utilizarea pe dispozitive \u00eencorporate \u0219i mobile, dimensiunea fi\u0219ierului comprimat cu modelul a fost redus\u0103 de la 188 MB la 47 MB (metoda de cuantificare a fost utilizat\u0103 dup\u0103 finalizarea antren\u0103rii modelului).\n<li class=\"l\"> Modelul lingvistic a fost transformat \u00eentr-un alt format de structur\u0103 de date, permi\u021b\u00e2nd realizarea map\u0103rii fi\u0219ierelor \u00een memorie la \u00eenc\u0103rcare. Suportul pentru vechiul format a fost oprit.\n<li class=\"l\"> Modul de \u00eenc\u0103rcare a fi\u0219ierului cu modelul lingvistic a fost modificat, ceea ce a permis reducerea consumului de memorie \u0219i diminuarea \u00eent\u00e2rzierilor la procesarea primei cereri dup\u0103 crearea modelului. \u00cen timpul func\u021bion\u0103rii, DeepSpeech consum\u0103 acum de 22 de ori mai pu\u021bin\u0103 memorie \u0219i se porne\u0219te de 500 de ori mai repede.\n<p><center><noindex><a rel=\"nofollow\" href=\"https:\/\/2r4s9p1yi1fa2jd7j43zph8r-wpengine.netdna-ssl.com\/files\/2019\/11\/startup_memory-1.png\"><img decoding=\"async\" alt=\"Compania Mozilla a prezentat motorul de recunoa\u0219tere a vorbirii DeepSpeech 0.6\" src=\"\/wp-content\/uploads\/2019\/12\/113ef11374da37383391cc886c488741.png\" style=\"display:block;margin: 0 auto;\" \/><\/a><\/noindex><\/center><\/p>\n<li class=\"l\"> A fost realizat\u0103 filtrarea cuvintelor rare \u00een modelul lingvistic. Num\u0103rul total de cuvinte a fost redus la 500 de mii cele mai populare cuvinte \u00eent\u00e2lnite \u00een textul folosit pentru antrenarea modelului. Cur\u0103\u021barea efectuat\u0103 a permis reducerea dimensiunii modelului lingvistic de la 1800 MB la 900 MB, av\u00e2nd un impact practic nesemnificativ asupra nivelului erorilor de recunoa\u0219tere.\n<li class=\"l\"> A fost ad\u0103ugat\u0103 suportul pentru diferite <noindex><a rel=\"nofollow\" href=\"https:\/\/github.com\/mozilla\/DeepSpeech\/commit\/58fdd55eea951dabd91a1158207f2228d745e657\">tehnici<\/a><\/noindex> de creare a unor varia\u021bii suplimentare (augmentation) a datelor audio utilizate \u00een timpul antren\u0103rii (de exemplu, ad\u0103ugarea unui set de variante, la care sunt introduse distorsiuni sau zgomote).\n<li class=\"l\"> A fost ad\u0103ugat\u0103 o bibliotec\u0103 cu leg\u0103turi pentru integrarea cu aplica\u021biile bazate pe platforma .NET.\n<li class=\"l\"> Documenta\u021bia a fost revizuit\u0103, fiind acum organizat\u0103 pe un site separat <noindex><a rel=\"nofollow\" href=\"https:\/\/deepspeech.readthedocs.io\/en\/latest\">deepspeech.readthedocs.io<\/a><\/noindex>.\n<\/ul>\n<p><noindex><a rel=\"nofollow\" name=\"link\"><\/a><\/noindex><\/p>\n<p>Sursa: <a \ncontent=\"nofollow\" rel=\"nofollow\" href=\"https:\/\/www.opennet.ru\/opennews\/art.shtml?num=51991\">opennet.ro<\/a><\/p>","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"excerpt":{"rendered":"<p>\u041f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u043b\u0435\u043d \u0432\u044b\u043f\u0443\u0441\u043a \u0440\u0430\u0437\u0432\u0438\u0432\u0430\u0435\u043c\u043e\u0433\u043e \u043a\u043e\u043c\u043f\u0430\u043d\u0438\u0435\u0439 Mozilla \u0434\u0432\u0438\u0436\u043a\u0430 \u0440\u0430\u0441\u043f\u043e\u0437\u043d\u0430\u0432\u0430\u043d\u0438\u044f \u0440\u0435\u0447\u0438 DeepSpeech 0.6, \u043a\u043e\u0442\u043e\u0440\u044b\u0439 \u0440\u0435\u0430\u043b\u0438\u0437\u0443\u0435\u0442 \u043e\u0434\u043d\u043e\u0438\u043c\u0451\u043d\u043d\u0443\u044e \u0430\u0440\u0445\u0438\u0442\u0435\u043a\u0442\u0443\u0440\u0443 \u0440\u0430\u0441\u043f\u043e\u0437\u043d\u0430\u0432\u0430\u043d\u0438\u044f \u0440\u0435\u0447\u0438, \u043f\u0440\u0435\u0434\u043b\u043e\u0436\u0435\u043d\u043d\u0443\u044e \u0438\u0441\u0441\u043b\u0435\u0434\u043e\u0432\u0430\u0442\u0435\u043b\u044f\u043c\u0438 \u0438\u0437 \u043a\u043e\u043c\u043f\u0430\u043d\u0438\u0438 Baidu. \u0420\u0435\u0430\u043b\u0438\u0437\u0430\u0446\u0438\u044f \u043d\u0430\u043f\u0438\u0441\u0430\u043d\u0430 \u043d\u0430 \u044f\u0437\u044b\u043a\u0435 Python \u0441 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043d\u0438\u0435\u043c \u043f\u043b\u0430\u0442\u0444\u043e\u0440\u043c\u044b \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f TensorFlow \u0438 \u0440\u0430\u0441\u043f\u0440\u043e\u0441\u0442\u0440\u0430\u043d\u044f\u0435\u0442\u0441\u044f \u043f\u043e\u0434 \u0441\u0432\u043e\u0431\u043e\u0434\u043d\u043e\u0439 \u043b\u0438\u0446\u0435\u043d\u0437\u0438\u0435\u0439 MPL 2.0. \u041f\u043e\u0434\u0434\u0435\u0440\u0436\u0438\u0432\u0430\u0435\u0442\u0441\u044f \u0440\u0430\u0431\u043e\u0442\u0430 \u0432 Linux, Android, macOS \u0438 Windows. \u041f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0438\u0442\u0435\u043b\u044c\u043d\u043e\u0441\u0442\u0438 \u0434\u043e\u0441\u0442\u0430\u0442\u043e\u0447\u043d\u043e \u0434\u043b\u044f \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043d\u0438\u044f \u0434\u0432\u0438\u0436\u043a\u0430 \u043d\u0430 \u043f\u043b\u0430\u0442\u0430\u0445 LePotato, [&hellip;]<\/p>\n","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"author":1,"featured_media":53723,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[702],"tags":[],"class_list":["post-53722","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news"],"aioseo_notices":[],"aioseo_head":"\n\t\t<!-- All in One SEO 5.0.2.1 - aioseo.com -->\n\t<meta name=\"description\" content=\"\u041f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u043b\u0435\u043d \u0432\u044b\u043f\u0443\u0441\u043a \u0440\u0430\u0437\u0432\u0438\u0432\u0430\u0435\u043c\u043e\u0433\u043e \u043a\u043e\u043c\u043f\u0430\u043d\u0438\u0435\u0439 Mozilla \u0434\u0432\u0438\u0436\u043a\u0430 \u0440\u0430\u0441\u043f\u043e\u0437\u043d\u0430\u0432\u0430\u043d\u0438\u044f \u0440\u0435\u0447\u0438\" \/>\n\t<meta name=\"robots\" content=\"max-image-preview:large\" \/>\n\t<meta name=\"author\" content=\"Yuri Gagarin\"\/>\n\t<link rel=\"canonical\" href=\"https:\/\/prohoster.info\/ro\/blog\/news\/kompaniya-mozilla-predstavila-dvizhok-raspoznavaniya-rechi-deepspeech-0-6\" \/>\n\t<meta name=\"generator\" content=\"All in One SEO (AIOSEO) 5.0.2.1\" \/>\n\t\t<meta property=\"og:locale\" content=\"ro_RO\" \/>\n\t\t<meta property=\"og:site_name\" content=\"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\" \/>\n\t\t<meta property=\"og:type\" content=\"article\" \/>\n\t\t<meta property=\"og:title\" content=\"\ud83e\udd47\u041a\u043e\u043c\u043f\u0430\u043d\u0438\u044f Mozilla \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u0438\u043b\u0430 \u0434\u0432\u0438\u0436\u043e\u043a \u0440\u0430\u0441\u043f\u043e\u0437\u043d\u0430\u0432\u0430\u043d\u0438\u044f \u0440\u0435\u0447\u0438 DeepSpeech 0.6 | ProHoster\" \/>\n\t\t<meta property=\"og:description\" content=\"\u041f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u043b\u0435\u043d \u0432\u044b\u043f\u0443\u0441\u043a \u0440\u0430\u0437\u0432\u0438\u0432\u0430\u0435\u043c\u043e\u0433\u043e \u043a\u043e\u043c\u043f\u0430\u043d\u0438\u0435\u0439 Mozilla \u0434\u0432\u0438\u0436\u043a\u0430 \u0440\u0430\u0441\u043f\u043e\u0437\u043d\u0430\u0432\u0430\u043d\u0438\u044f \u0440\u0435\u0447\u0438\" \/>\n\t\t<meta property=\"og:url\" content=\"https:\/\/prohoster.info\/ro\/blog\/news\/kompaniya-mozilla-predstavila-dvizhok-raspoznavaniya-rechi-deepspeech-0-6\" \/>\n\t\t<meta property=\"og:image\" content=\"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg\" \/>\n\t\t<meta property=\"og:image:secure_url\" content=\"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg\" \/>\n\t\t<meta property=\"og:image:width\" content=\"350\" \/>\n\t\t<meta property=\"og:image:height\" content=\"350\" \/>\n\t\t<meta property=\"article:published_time\" content=\"2019-12-07T21:00:00+00:00\" \/>\n\t\t<meta property=\"article:modified_time\" content=\"2020-02-18T11:01:39+00:00\" \/>\n\t\t<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/prohoster\" \/>\n\t\t<meta property=\"article:author\" content=\"https:\/\/www.facebook.com\/prohoster\" \/>\n\t\t<!-- All in One SEO -->\n\n","aioseo_head_json":{"title":"\ud83e\udd47Compania Mozilla a prezentat motorul de recunoa\u0219tere vocal\u0103 DeepSpeech 0.6 | ProHoster","description":"A fost lansat\u0103 o versiune a motorului de recunoa\u0219tere vocal\u0103 dezvoltat de Mozilla","canonical_url":"https:\/\/prohoster.info\/ro\/blog\/news\/kompaniya-mozilla-predstavila-dvizhok-raspoznavaniya-rechi-deepspeech-0-6","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\u041a\u043e\u043c\u043f\u0430\u043d\u0438\u044f Mozilla \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u0438\u043b\u0430 \u0434\u0432\u0438\u0436\u043e\u043a \u0440\u0430\u0441\u043f\u043e\u0437\u043d\u0430\u0432\u0430\u043d\u0438\u044f \u0440\u0435\u0447\u0438 DeepSpeech 0.6 | ProHoster","og:description":"\u041f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u043b\u0435\u043d \u0432\u044b\u043f\u0443\u0441\u043a \u0440\u0430\u0437\u0432\u0438\u0432\u0430\u0435\u043c\u043e\u0433\u043e \u043a\u043e\u043c\u043f\u0430\u043d\u0438\u0435\u0439 Mozilla \u0434\u0432\u0438\u0436\u043a\u0430 \u0440\u0430\u0441\u043f\u043e\u0437\u043d\u0430\u0432\u0430\u043d\u0438\u044f \u0440\u0435\u0447\u0438","og:url":"https:\/\/prohoster.info\/ro\/blog\/news\/kompaniya-mozilla-predstavila-dvizhok-raspoznavaniya-rechi-deepspeech-0-6","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":"2019-12-07T21:00:00+00:00","article:modified_time":"2020-02-18T11:01:39+00:00","article:publisher":"https:\/\/www.facebook.com\/prohoster","article:author":"https:\/\/www.facebook.com\/prohoster"},"aioseo_meta_data":{"post_id":"53722","title":null,"description":null,"keywords":null,"keyphrases":null,"primary_term":null,"canonical_url":null,"og_title":null,"og_description":null,"og_object_type":"default","og_image_type":"default","og_image_url":null,"og_image_width":null,"og_image_height":null,"og_image_custom_url":null,"og_image_custom_fields":null,"og_video":null,"og_custom_url":null,"og_article_section":null,"og_article_tags":null,"twitter_use_og":false,"twitter_card":"default","twitter_image_type":"default","twitter_image_url":null,"twitter_image_custom_url":null,"twitter_image_custom_fields":null,"twitter_title":null,"twitter_description":null,"schema":{"blockGraphs":[],"customGraphs":[],"default":{"data":{"Article":[],"Course":[],"Dataset":[],"FAQPage":[],"Movie":[],"Person":[],"Product":[],"ProductReview":[],"Car":[],"Recipe":[],"Service":[],"SoftwareApplication":[],"WebPage":[]},"graphName":"","isEnabled":true},"graphs":[]},"schema_type":null,"schema_type_options":null,"pillar_content":false,"robots_default":true,"robots_noindex":false,"robots_noarchive":false,"robots_nosnippet":false,"robots_nofollow":false,"robots_noimageindex":false,"robots_noodp":false,"robots_notranslate":false,"robots_max_snippet":null,"robots_max_videopreview":null,"robots_max_imagepreview":"large","priority":null,"frequency":null,"local_seo":null,"seo_analyzer_scan_date":"2026-01-24 08:28:20","breadcrumb_settings":null,"limit_modified_date":false,"reviewed_by":null,"ai":null,"created":"2021-02-28 20:19:21","updated":"2026-01-24 08:28:20","focus_keyword":null,"additional_keywords":null,"truseo_locale":null},"gt_translate_keys":[{"key":"link","format":"url"}],"_links":{"self":[{"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/posts\/53722","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=53722"}],"version-history":[{"count":0,"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/posts\/53722\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/media\/53723"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/media?parent=53722"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/categories?post=53722"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/tags?post=53722"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}