{"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\/sk\/blog\/news\/kompaniya-mozilla-predstavila-dvizhok-raspoznavaniya-rechi-deepspeech-0-6","title":{"rendered":"Spolo\u010dnos\u0165 Mozilla predstavila engine pre rozpozn\u00e1vanie re\u010di 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\/\">Predstaven\u00e9<\/a><\/noindex> vydanie v\u00fdvojov\u00e9ho motora na rozpozn\u00e1vanie re\u010di spolo\u010dnosti Mozilla <noindex><a rel=\"nofollow\" href=\"https:\/\/github.com\/mozilla\/DeepSpeech\/releases\/v0.6.0\">DeepSpeech 0.6<\/a><\/noindex>, ktor\u00fd implementuje rovnomenn\u00fa architekt\u00faru rozpozn\u00e1vania re\u010di, <noindex><a rel=\"nofollow\" href=\"https:\/\/arxiv.org\/abs\/1412.5567\">navrhnut\u00fa<\/a><\/noindex> v\u00fdskumn\u00edkmi zo spolo\u010dnosti Baidu. Implement\u00e1cia je nap\u00edsan\u00e1 v jazyku Python s vyu\u017eit\u00edm platformy strojov\u00e9ho u\u010denia TensorFlow a <noindex><a rel=\"nofollow\" href=\"https:\/\/github.com\/mozilla\/DeepSpeech\">distribuovan\u00fd<\/a><\/noindex> pod vo\u013enou licenciou MPL 2.0. Podporuje pr\u00e1cu v Linuxe, Androide, macOS a Windows. V\u00fdkon je dostato\u010dn\u00fd na pou\u017eitie motora na dosk\u00e1ch LePotato, Raspberry Pi 3 a Raspberry Pi 4.<\/p>\n<p>V s\u00faprave s\u00fa tie\u017e <noindex><a rel=\"nofollow\" href=\"https:\/\/github.com\/mozilla\/DeepSpeech\/releases\/download\/v0.6.0\/deepspeech-0.6.0-models.tar.gz\">s\u00fa k dispoz\u00edcii<\/a><\/noindex> vy\u0161kolen\u00e9 modely, <noindex><a rel=\"nofollow\" href=\"https:\/\/github.com\/mozilla\/DeepSpeech\/releases\/download\/v0.6.0\/audio-0.6.0.tar.gz\">rotuj\u00facich lopatiek pre VSPAERO;<\/a><\/noindex> zvukov\u00fdch s\u00faborov a n\u00e1stroj pre rozpozn\u00e1vanie z pr\u00edkazov\u00e9ho riadku. Na integr\u00e1ciu funkcie rozpozn\u00e1vania re\u010di do svojich programov s\u00fa k dispoz\u00edcii hotov\u00e9 moduly pre Python, NodeJS, C++ a .NET (extern\u00ed v\u00fdvoj\u00e1ri samostatne pripravili moduly pre <noindex><a rel=\"nofollow\" href=\"https:\/\/github.com\/RustAudio\/deepspeech-rs\">Rust<\/a><\/noindex> a <noindex><a rel=\"nofollow\" href=\"https:\/\/github.com\/asticode\/go-astideepspeech\">Go<\/a><\/noindex>). Hotov\u00fd model je dod\u00e1van\u00fd len pre anglick\u00fd jazyk, ale pre in\u00e9 jazyky sa <noindex><a rel=\"nofollow\" href=\"https:\/\/github.com\/mozilla\/DeepSpeech\/wiki#how-can-i-train-using-my-own-data\">prilo\u017een\u00fdm<\/a><\/noindex> <noindex><a rel=\"nofollow\" href=\"https:\/\/github.com\/mozilla\/DeepSpeech\/blob\/master\/TRAINING.rst#common-voice-training-data\">the instructions<\/a><\/noindex> m\u00f4\u017ee syst\u00e9m natr\u00e9nova\u0165 samostatne, vyu\u017eit\u00edm <noindex><a rel=\"nofollow\" href=\"https:\/\/voice.mozilla.org\/en\/datasets\">hlasov\u00fdch d\u00e1t<\/a><\/noindex>, zhroma\u017eden\u00fdch projektom Common Voice. <\/p>\n<p>DeepSpeech je v\u00fdrazne jednoduch\u0161\u00ed ako tradi\u010dn\u00e9 syst\u00e9my a poskytuje vy\u0161\u0161iu kvalitu rozpozn\u00e1vania aj pri pr\u00edtomnosti okolit\u00e9ho hluku. Pri v\u00fdvoji sa nepou\u017e\u00edvaj\u00fa tradi\u010dn\u00e9 akustick\u00e9 modely a koncept fon\u00e9m, namiesto toho sa vyu\u017e\u00edva dobre optimalizovan\u00fd syst\u00e9m strojov\u00e9ho u\u010denia zalo\u017een\u00fd na neur\u00f3novej sieti, ktor\u00fd umo\u017e\u0148uje ob\u00eds\u0165 v\u00fdvoj jednotliv\u00fdch komponentov na modelovanie r\u00f4znych odch\u00fdlok, ako s\u00fa hluk, ozvena a charakteristiky re\u010di. <\/p>\n<p>Nev\u00fdhodou tak\u00e9ho pr\u00edstupu je, \u017ee na dosiahnutie kvalitn\u00e9ho rozpozn\u00e1vania a tr\u00e9ningu neur\u00f3novej siete motor DeepSpeech vy\u017eaduje ve\u013ek\u00e9 mno\u017estvo rozmanit\u00fdch \u00fadajov, nadiktovan\u00fdch v re\u00e1lnych podmienkach r\u00f4znymi hlasmi a za pr\u00edtomnosti prirodzen\u00e9ho hluku.<br \/>\nZber tak\u00fdchto \u00fadajov zabezpe\u010duje projekt vytvoren\u00fd v Mozille <noindex><a rel=\"nofollow\" href=\"https:\/\/voice.mozilla.org\/\">Common Voice<\/a><\/noindex>, ktor\u00fd poskytuje overen\u00fa datab\u00e1zu s 780 hodinami v <noindex><a rel=\"nofollow\" href=\"https:\/\/voice.mozilla.org\/en\/datasets\">angli\u010dtine<\/a><\/noindex>, 325 v nem\u010dine, 173 vo franc\u00faz\u0161tine a 27 hodinami v ru\u0161tine. <\/p>\n<p>Cie\u013eom projektu Common Voice je zhroma\u017edi\u0165 10 000 hod\u00edn nahr\u00e1vok r\u00f4znych v\u00fdslovnost\u00ed typov\u00fdch fr\u00e1z \u013eudskej re\u010di, \u010do umo\u017en\u00ed dosiahnu\u0165 akceptovate\u013en\u00fa \u00farove\u0148 ch\u00fdb pri rozpozn\u00e1van\u00ed. V s\u00fa\u010dasnosti \u00fa\u010dastn\u00edci projektu nahrali u\u017e 4,3 tis\u00edc hod\u00edn, z ktor\u00fdch 3,5 tis\u00edc pre\u0161lo kontrolou. Pri v\u00fdu\u010dbe kone\u010dn\u00e9ho modelu anglick\u00e9ho jazyka pre DeepSpeech sa pou\u017eilo 3 816 hod\u00edn re\u010di, okrem Common Voice zah\u0155\u0148aj\u00face d\u00e1ta z projektov LibriSpeech, Fisher a Switchboard, ako aj pribli\u017ene 1 700 hod\u00edn transkribovan\u00fdch nahr\u00e1vok rozhlasov\u00fdch rel\u00e1ci\u00ed.<\/p>\n<p>Pri pou\u017eit\u00ed pon\u00fakanej modelu anglick\u00e9ho jazyka na stiahnutie je \u00farove\u0148 ch\u00fdb rozpozn\u00e1vania v DeepSpeech 7,5 % pri hodnoten\u00ed testovac\u00edm s\u00faborom. <noindex><a rel=\"nofollow\" href=\"http:\/\/www.openslr.org\/12\/\">LibriSpeech<\/a><\/noindex>. Pre porovnanie, \u00farove\u0148 ch\u00fdb pri rozpozn\u00e1van\u00ed \u010dlovekom <noindex><a rel=\"nofollow\" href=\"https:\/\/arxiv.org\/pdf\/1412.5567v1.pdf\">sa hodnot\u00ed<\/a><\/noindex> na 5,83%.<\/p>\n<p>DeepSpeech sa sklad\u00e1 z dvoch subsyst\u00e9mov - akustick\u00e9ho modelu a dekod\u00e9ra. Akustick\u00fd model vyu\u017e\u00edva met\u00f3dy h\u013abkov\u00e9ho strojov\u00e9ho u\u010denia na v\u00fdpo\u010det pravdepodobnosti v\u00fdskytu ur\u010dit\u00fdch symbolov v prijatom zvuku. Dekod\u00e9r aplikuje algoritmus vyh\u013ead\u00e1vania po l\u00fa\u010doch na prevedenie \u00fadajov o pravdepodobnosti symbolov na textov\u00fa reprezent\u00e1ciu.<\/p>\n<p>Hlavn\u00e9 <noindex><a rel=\"nofollow\" href=\"https:\/\/github.com\/mozilla\/DeepSpeech\/releases\/v0.6.0\">novinky<\/a><\/noindex> DeepSpeech 0.6 (vetva 0.6 nie je kompatibiln\u00e1 s predch\u00e1dzaj\u00facimi verziami a vy\u017eaduje aktualiz\u00e1ciu k\u00f3du a modelov):<\/p>\n<ul>\n<li class=\"l\"> Bol navrhnut\u00fd nov\u00fd streamovac\u00ed dekod\u00e9r, ktor\u00fd zabezpe\u010duje vy\u0161\u0161iu reak\u010dn\u00fa r\u00fdchlos\u0165 a nez\u00e1vis\u00ed od ve\u013ekosti spracov\u00e1van\u00fdch zvukov\u00fdch d\u00e1t. V d\u00f4sledku toho sa v novej verzii DeepSpeech podarilo zn\u00ed\u017ei\u0165 latenciu rozpozn\u00e1vania na 260 ms, \u010do je o 73 % r\u00fdchlej\u0161ie ako predt\u00fdm a umo\u017e\u0148uje pou\u017ei\u0165 DeepSpeech v rie\u0161eniach na rozpozn\u00e1vanie re\u010di v re\u00e1lnom \u010dase.\n<li class=\"l\"> Boli zaveden\u00e9 zmeny v API a uskuto\u010dnila sa pr\u00e1ca na zjednoten\u00ed n\u00e1zvov funkci\u00ed. Pridan\u00e9 funkcie pre z\u00edskanie \u010fal\u0161\u00edch metad\u00e1t o synchroniz\u00e1cii, ktor\u00e9 umo\u017e\u0148uj\u00fa nielen z\u00edska\u0165 textov\u00fa reprezent\u00e1ciu, ale aj sledova\u0165 spojenie jednotliv\u00fdch znakov a viet s poz\u00edciou v zvukovom pr\u00fade.\n<li class=\"l\"> Do n\u00e1strojov pre v\u00fdu\u010dbu modulov bola pridan\u00e1 podpora pre pou\u017eitie kni\u017enice <noindex><a rel=\"nofollow\" href=\"https:\/\/developer.nvidia.com\/cudnn\">CuDNN<\/a><\/noindex> na optimaliz\u00e1ciu pr\u00e1ce s rekurentn\u00fdmi neur\u00f3nov\u00fdmi sie\u0165ami (RNN), \u010do viedlo k v\u00fdrazn\u00e9mu (pribli\u017ene dvojn\u00e1sobn\u00e9mu) zv\u00fd\u0161eniu v\u00fdkonu u\u010denia modelu, av\u0161ak si to vy\u017eadovalo zmeny v k\u00f3de, ktor\u00e9 naru\u0161ili kompatibilitu s predt\u00fdm pripraven\u00fdmi modelmi.\n<li class=\"l\"> Minim\u00e1lne po\u017eiadavky na verziu TensorFlow boli zv\u00fd\u0161en\u00e9 z 1.13.1 na 1.14.0. Pridan\u00e1 podpora \u013eahkej ed\u00edcie TensorFlow Lite, pri pou\u017eit\u00ed ktorej sa ve\u013ekos\u0165 bal\u00edka DeepSpeech zmen\u0161ila z 98 MB na 3.7 MB. Pre pou\u017eitie na vstavan\u00fdch a mobiln\u00fdch zariadeniach tie\u017e klesla ve\u013ekos\u0165 zabalen\u00e9ho s\u00faboru s modelom z 188 MB na 47 MB (na kompresiu bol pou\u017eit\u00fd met\u00f3da kvantovania po dokon\u010den\u00ed u\u010denia modelu).\n<li class=\"l\"> Jazykov\u00fd model bol preveden\u00fd na in\u00fd form\u00e1t \u0161trukt\u00far d\u00e1t, ktor\u00fd umo\u017e\u0148uje mapovanie s\u00faborov do pam\u00e4te pri na\u010d\u00edtan\u00ed. Podpora star\u00e9ho form\u00e1tu bola ukon\u010den\u00e1.\n<li class=\"l\"> Bol zmenen\u00fd re\u017eim na\u010d\u00edtania s\u00faboru s jazykov\u00fdm modelom, \u010do umo\u017enilo zn\u00ed\u017ei\u0165 spotrebu pam\u00e4te a zmen\u0161i\u0165 oneskorenia pri spracovan\u00ed prv\u00e9ho dopytu po vytvoren\u00ed modelu. V priebehu pr\u00e1ce DeepSpeech teraz spotrebuje 22-kr\u00e1t menej pam\u00e4te a sp\u00fa\u0161\u0165a sa 500-kr\u00e1t r\u00fdchlej\u0161ie.\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=\"Spolo\u010dnos\u0165 Mozilla predstavila engine pre rozpozn\u00e1vanie re\u010di 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\"> Bola vykonan\u00e1 filtr\u00e1cia zriedkav\u00fdch slov v jazykovom modeli. Celkov\u00fd po\u010det slov bol zn\u00ed\u017een\u00fd na 500 tis\u00edc najpopul\u00e1rnej\u0161\u00edch slov, ktor\u00e9 sa vyskytuj\u00fa v texte pou\u017eitom pri tr\u00e9ningu modelu. Uskuto\u010dnen\u00e9 \u010distenie umo\u017enilo zn\u00ed\u017ei\u0165 ve\u013ekos\u0165 jazykov\u00e9ho modelu z 1800MB na 900MB, pri\u010dom to takmer nijako neovplyvnilo ukazovatele \u00farovne ch\u00fdb rozpozn\u00e1vania.\n<li class=\"l\"> Pridan\u00e1 podpora r\u00f4znych <noindex><a rel=\"nofollow\" href=\"https:\/\/github.com\/mozilla\/DeepSpeech\/commit\/58fdd55eea951dabd91a1158207f2228d745e657\">techn\u00edk<\/a><\/noindex> tvorby dodato\u010dn\u00fdch vari\u00e1ci\u00ed (augmentation) zvukov\u00fdch d\u00e1t pou\u017e\u00edvan\u00fdch pri u\u010den\u00ed (napr\u00edklad prid\u00e1vanie k s\u00faboru variantov, do ktor\u00fdch boli zahrnut\u00e9 skreslenia alebo \u0161umy).\n<li class=\"l\"> Pridan\u00e1 kni\u017enica s bindingami pre integr\u00e1ciu s aplik\u00e1ciami na b\u00e1ze platformy .NET.\n<li class=\"l\"> Prepracovan\u00e1 dokument\u00e1cia, ktor\u00e1 je teraz zhroma\u017eden\u00e1 na samostatnej str\u00e1nke <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>Zdroj: <a \ncontent=\"nofollow\" rel=\"nofollow\" href=\"https:\/\/www.opennet.ru\/opennews\/art.shtml?num=51991\">opennet.ru<\/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 5.0.4 - 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\/sk\/blog\/news\/kompaniya-mozilla-predstavila-dvizhok-raspoznavaniya-rechi-deepspeech-0-6\" \/>\n\t\t<meta name=\"generator\" content=\"All in One SEO (AIOSEO) 5.0.4\" \/>\n\t\t<meta property=\"og:locale\" content=\"sk_SK\" \/>\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\/sk\/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\udd47Spolo\u010dnos\u0165 Mozilla predstavila motor rozpozn\u00e1vania re\u010di DeepSpeech 0.6 | ProHoster","description":"Bol predstaven\u00fd vydanie vyv\u00edjan\u00e9ho spolo\u010dnos\u0165ou Mozilla motora rozpozn\u00e1vania re\u010di","canonical_url":"https:\/\/prohoster.info\/sk\/blog\/news\/kompaniya-mozilla-predstavila-dvizhok-raspoznavaniya-rechi-deepspeech-0-6","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\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\/sk\/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\/sk\/wp-json\/wp\/v2\/posts\/53722","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=53722"}],"version-history":[{"count":0,"href":"https:\/\/prohoster.info\/sk\/wp-json\/wp\/v2\/posts\/53722\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/prohoster.info\/sk\/wp-json\/wp\/v2\/media\/53723"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/sk\/wp-json\/wp\/v2\/media?parent=53722"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/sk\/wp-json\/wp\/v2\/categories?post=53722"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/sk\/wp-json\/wp\/v2\/tags?post=53722"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}