{"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\/hu\/blog\/news\/kompaniya-mozilla-predstavila-dvizhok-raspoznavaniya-rechi-deepspeech-0-6","title":{"rendered":"A Mozilla bemutatta a 0.6-os DeepSpeech besz\u00e9dfelismer\u0151 motorj\u00e1t","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\/\">Bemutatva<\/a><\/noindex> a Mozilla \u00e1ltal fejlesztett besz\u00e9dfelismer\u0151 motor kiad\u00e1sa <noindex><a rel=\"nofollow\" href=\"https:\/\/github.com\/mozilla\/DeepSpeech\/releases\/v0.6.0\">DeepSpeech 0.6<\/a><\/noindex>, amely megval\u00f3s\u00edtja az azonos nev\u0171 besz\u00e9dfelismer\u00e9si architekt\u00far\u00e1t, <noindex><a rel=\"nofollow\" href=\"https:\/\/arxiv.org\/abs\/1412.5567\">amit<\/a><\/noindex> a Baidu kutat\u00f3i javasoltak. A megval\u00f3s\u00edt\u00e1s Python nyelven k\u00e9sz\u00fclt a TensorFlow g\u00e9pi tanul\u00e1si platform haszn\u00e1lat\u00e1val \u00e9s <noindex><a rel=\"nofollow\" href=\"https:\/\/github.com\/mozilla\/DeepSpeech\">terjeszt\u00e9sre ker\u00fcl<\/a><\/noindex> MPL 2.0 szabad licenc alatt. T\u00e1mogatja a m\u0171k\u00f6d\u00e9st Linux, Android, macOS \u00e9s Windows rendszereken. A teljes\u00edtm\u00e9ny elegend\u0151 a motor haszn\u00e1lat\u00e1hoz LePotato, Raspberry Pi 3 \u00e9s Raspberry Pi 4 platformokon.<\/p>\n<p>A csomagban tal\u00e1lhat\u00f3ak <noindex><a rel=\"nofollow\" href=\"https:\/\/github.com\/mozilla\/DeepSpeech\/releases\/download\/v0.6.0\/deepspeech-0.6.0-models.tar.gz\">k\u00edn\u00e1lj\u00e1k<\/a><\/noindex> k\u00e9pzett modellek, <noindex><a rel=\"nofollow\" href=\"https:\/\/github.com\/mozilla\/DeepSpeech\/releases\/download\/v0.6.0\/audio-0.6.0.tar.gz\">p\u00e9ld\u00e1kat<\/a><\/noindex> hangf\u00e1jlok \u00e9s parancssori felismer\u00e9shez sz\u00fcks\u00e9ges eszk\u00f6z\u00f6k is. A besz\u00e9dfelismer\u00e9si funkci\u00f3 beintegr\u00e1l\u00e1s\u00e1hoz az alkalmaz\u00e1sokba k\u00e9sz modulok \u00e1llnak rendelkez\u00e9sre Python, NodeJS, C++ \u00e9s .NET sz\u00e1m\u00e1ra (k\u00fcl\u00f6n fejleszt\u0151k \u00e1ltal k\u00e9sz\u00edtett modulok a <noindex><a rel=\"nofollow\" href=\"https:\/\/github.com\/RustAudio\/deepspeech-rs\">Rust<\/a><\/noindex> \u00e9s <noindex><a rel=\"nofollow\" href=\"https:\/\/github.com\/asticode\/go-astideepspeech\">Go<\/a><\/noindex>). A k\u00e9sz modell csak angol nyelven \u00e1ll rendelkez\u00e9sre, de m\u00e1s nyelvek eset\u00e9n a <noindex><a rel=\"nofollow\" href=\"https:\/\/github.com\/mozilla\/DeepSpeech\/wiki#how-can-i-train-using-my-own-data\">mell\u00e9kelt<\/a><\/noindex> <noindex><a rel=\"nofollow\" href=\"https:\/\/github.com\/mozilla\/DeepSpeech\/blob\/master\/TRAINING.rst#common-voice-training-data\">utas\u00edt\u00e1st<\/a><\/noindex> rendszert \u00f6n\u00e1ll\u00f3an is ki lehet k\u00e9pezni <noindex><a rel=\"nofollow\" href=\"https:\/\/voice.mozilla.org\/en\/datasets\">hangadatokb\u00f3l,<\/a><\/noindex>amelyeket a Common Voice projekt gy\u0171jt\u00f6tt. <\/p>\n<p>A DeepSpeech jelent\u0151sen egyszer\u0171bb, mint a hagyom\u00e1nyos rendszerek, r\u00e1ad\u00e1sul magasabb felismer\u00e9si min\u0151s\u00e9get biztos\u00edt k\u00fcls\u0151 zaj jelenl\u00e9t\u00e9ben. A fejleszt\u00e9s sor\u00e1n nem haszn\u00e1lnak hagyom\u00e1nyos akusztikai modelleket \u00e9s fon\u00e9m\u00e1k koncepci\u00f3j\u00e1t, ehelyett egy j\u00f3l optimaliz\u00e1lt, neur\u00e1lis h\u00e1l\u00f3zat alap\u00fa g\u00e9pi tanul\u00e1si rendszert alkalmaznak, amely lehet\u0151v\u00e9 teszi, hogy k\u00fcl\u00f6n komponensek kidolgoz\u00e1sa n\u00e9lk\u00fcl modellezz\u00e9k a k\u00fcl\u00f6nb\u00f6z\u0151 zajokat, p\u00e9ld\u00e1ul a zajt, az visszhangot \u00e9s a besz\u00e9d saj\u00e1toss\u00e1gait. <\/p>\n<p>E megk\u00f6zel\u00edt\u00e9s h\u00e1tr\u00e1nya, hogy a megfelel\u0151 felismer\u00e9s \u00e9s a neur\u00e1lis h\u00e1l\u00f3zat kik\u00e9pz\u00e9s\u00e9hez a DeepSpeech motor nagy mennyis\u00e9g\u0171 k\u00fcl\u00f6nf\u00e9le adatra van sz\u00fcks\u00e9ge, amelyeket val\u00f3s k\u00f6r\u00fclm\u00e9nyek k\u00f6z\u00f6tt, k\u00fcl\u00f6nb\u00f6z\u0151 hangokkal \u00e9s term\u00e9szetes zajok mellett dikt\u00e1lnak.<br \/>\nEzeket az adatokat a Mozilla \u00e1ltal l\u00e9trehozott projekt gy\u0171jti, <noindex><a rel=\"nofollow\" href=\"https:\/\/voice.mozilla.org\/\">Common Voice<\/a><\/noindex>amely ellen\u0151rz\u00f6tt adathalmazt biztos\u00edt 780 \u00f3r\u00e1nyi <noindex><a rel=\"nofollow\" href=\"https:\/\/voice.mozilla.org\/en\/datasets\">angol nyelven,<\/a><\/noindex>325 \u00f3r\u00e1j\u00e1val n\u00e9met\u00fcl, 173 \u00f3r\u00e1j\u00e1val franci\u00e1ul \u00e9s 27 \u00f3r\u00e1j\u00e1val oroszul. <\/p>\n<p>A Common Voice projekt v\u00e9gs\u0151 c\u00e9lja 10 ezer \u00f3ra emberi besz\u00e9d k\u00fcl\u00f6nb\u00f6z\u0151 kiejt\u00e9seinek felv\u00e9tele, ami lehet\u0151v\u00e9 teszi az elfogadhat\u00f3 hiba szint el\u00e9r\u00e9s\u00e9t a hangfelismer\u00e9sben. Jelen \u00e1llapot szerint a projekt r\u00e9sztvev\u0151i \u00f6sszesen 4,3 ezer \u00f3r\u00e1nyi anyagot dikt\u00e1ltak le, ebb\u0151l 3,5 ezer \u00f3ra ellen\u0151rz\u00e9sen esett \u00e1t. A DeepSpeech v\u00e9gs\u0151 angol nyelv\u0171 modellj\u00e9nek tan\u00edt\u00e1sa sor\u00e1n 3816 \u00f3r\u00e1nyi besz\u00e9det haszn\u00e1ltak, a Common Voice-on k\u00edv\u00fcl, amely adatokkal szolg\u00e1l a LibriSpeech, Fisher \u00e9s Switchboard projektekb\u0151l, valamint k\u00f6r\u00fclbel\u00fcl 1700 \u00f3ra r\u00e1di\u00f3m\u0171sorok \u00e1tirat\u00e1val is rendelkezik.<\/p>\n<p>A let\u00f6lt\u00e9sre k\u00edn\u00e1lt angol nyelv\u0171 modell haszn\u00e1latakor a DeepSpeech hibaszintje 7,5%, ha tesztcsoporttal \u00e9rt\u00e9kelj\u00fck. <noindex><a rel=\"nofollow\" href=\"http:\/\/www.openslr.org\/12\/\">LibriSpeech<\/a><\/noindex>. \u00d6sszehasonl\u00edt\u00e1sk\u00e9nt az emberi hangfelismer\u00e9s <noindex><a rel=\"nofollow\" href=\"https:\/\/arxiv.org\/pdf\/1412.5567v1.pdf\">\u00e9rt\u00e9kel\u00e9se<\/a><\/noindex> 5,83%-ra r\u00fag.<\/p>\n<p>A DeepSpeech k\u00e9t alrendszerb\u0151l \u00e1ll - akusztikus modellb\u0151l \u00e9s dek\u00f3derb\u0151l. Az akusztikus modell m\u00e9lyg\u00e9pi tanul\u00e1si m\u00f3dszereket haszn\u00e1l a bemeneti hangban el\u0151fordul\u00f3 bizonyos karakterek val\u00f3sz\u00edn\u0171s\u00e9g\u00e9nek kisz\u00e1m\u00edt\u00e1s\u00e1hoz. A dek\u00f3der sug\u00e1rkeres\u00e9si algoritmust alkalmaz a karakterek val\u00f3sz\u00edn\u0171s\u00e9gi adatainak sz\u00f6veges megjelen\u00edt\u00e9ss\u00e9 alak\u00edt\u00e1s\u00e1hoz.<\/p>\n<p>F\u0151 <noindex><a rel=\"nofollow\" href=\"https:\/\/github.com\/mozilla\/DeepSpeech\/releases\/v0.6.0\">\u00fajdons\u00e1gok<\/a><\/noindex> DeepSpeech 0.6 (a 0.6-os \u00e1g nem kompatibilis a kor\u00e1bbi kiad\u00e1sokkal, friss\u00edt\u00e9s sz\u00fcks\u00e9ges a k\u00f3dhoz \u00e9s modellekhez):<\/p>\n<ul>\n<li class=\"l\"> \u00daj folyamat dek\u00f3der ker\u00fclt javaslatra, amely magasabb v\u00e1laszk\u00e9szs\u00e9get biztos\u00edt, f\u00fcggetlen\u00fcl a feldolgozott hangadatok m\u00e9ret\u00e9t\u0151l. Ennek eredm\u00e9nyek\u00e9nt a DeepSpeech \u00faj verzi\u00f3j\u00e1ban a hangfelismer\u00e9si k\u00e9sleked\u00e9st 260 ms-ra siker\u00fclt cs\u00f6kkenteni, ami 73%-kal gyorsabb, mint kor\u00e1bban, \u00e9s lehet\u0151v\u00e9 teszi a DeepSpeech alkalmaz\u00e1s\u00e1t val\u00f3s idej\u0171 besz\u00e9dfelismer\u00e9si megold\u00e1sokban.\n<li class=\"l\"> V\u00e1ltoz\u00e1sok t\u00f6rt\u00e9ntek az API-ban, \u00e9s a funkci\u00f3nevek egys\u00e9ges\u00edt\u00e9s\u00e9n is dolgoztak. \u00daj funkci\u00f3k ker\u00fcltek hozz\u00e1ad\u00e1sra a szinkroniz\u00e1l\u00e1s tov\u00e1bbi metaadatainak megszerz\u00e9s\u00e9hez, lehet\u0151v\u00e9 t\u00e9ve nemcsak a sz\u00f6veges \u00e1br\u00e1zol\u00e1s kinyer\u00e9s\u00e9t, hanem az egyes karakterek \u00e9s mondatok hangfolyamban val\u00f3 poz\u00edci\u00f3ra val\u00f3 vonatkoztat\u00e1s\u00e1nak nyomon k\u00f6vet\u00e9s\u00e9t is.\n<li class=\"l\"> A tanul\u00e1si modulok eszk\u00f6zt\u00e1r\u00e1hoz hozz\u00e1adva a CuDNN k\u00f6nyvt\u00e1r haszn\u00e1lat\u00e1nak t\u00e1mogat\u00e1sa is megjelent. <noindex><a rel=\"nofollow\" href=\"https:\/\/developer.nvidia.com\/cudnn\">CuDNN<\/a><\/noindex> Rekurz\u00edv neur\u00e1lis h\u00e1l\u00f3zatok (RNN) optimaliz\u00e1l\u00e1s\u00e1hoz k\u00e9sz\u00fclt, ami lehet\u0151v\u00e9 tette a modell tanul\u00e1si teljes\u00edtm\u00e9ny\u00e9nek k\u00f6r\u00fclbel\u00fcl k\u00e9tszeres n\u00f6vel\u00e9s\u00e9t, de a k\u00f3d m\u00f3dos\u00edt\u00e1sait ig\u00e9nyelte, amelyek megs\u00e9rtett\u00e9k a kor\u00e1bban k\u00e9sz\u00fclt modellekkel val\u00f3 kompatibilit\u00e1st.\n<li class=\"l\"> A TensorFlow minimalis k\u00f6vetelm\u00e9nyei 1.13.1-r\u0151l 1.14.0-ra emelkedtek. Hozz\u00e1adt\u00e1k a TensorFlow Lite k\u00f6nny\u0171s\u00faly\u00fa kiad\u00e1s\u00e1nak t\u00e1mogat\u00e1s\u00e1t, amelynek haszn\u00e1lat\u00e1val a DeepSpeech csomagm\u00e9rete 98 MB-r\u00f3l 3.7 MB-ra cs\u00f6kkent. Be\u00e9p\u00edtett \u00e9s mobil eszk\u00f6z\u00f6k eset\u00e9n a csomagolt f\u00e1jl m\u00e9rete szint\u00e9n cs\u00f6kkent 188 MB-r\u00f3l 47 MB-ra (a modellt a tanul\u00e1s befejez\u00e9se ut\u00e1n v\u00e9gzett kvant\u00e1l\u00e1si m\u00f3dszerrel t\u00f6m\u00f6r\u00edtett\u00e9k).\n<li class=\"l\"> A nyelvi modellt egy m\u00e1sik adatstrukt\u00fara-form\u00e1tumra alak\u00edtott\u00e1k \u00e1t, amely lehet\u0151v\u00e9 teszi a f\u00e1jlok mem\u00f3ria-t\u00e9rk\u00e9pez\u00e9s\u00e9t bet\u00f6lt\u00e9skor. A r\u00e9gi form\u00e1tum t\u00e1mogat\u00e1sa megsz\u0171nt.\n<li class=\"l\"> Megv\u00e1ltozott a nyelvi modellel rendelkez\u0151 f\u00e1jl bet\u00f6lt\u00e9si m\u00f3dja, amely cs\u00f6kkentette a mem\u00f3riafogyaszt\u00e1st \u00e9s cs\u00f6kkentette az els\u0151 k\u00e9r\u00e9s feldolgoz\u00e1si k\u00e9sleltet\u00e9s\u00e9t a modell l\u00e9trehoz\u00e1sa ut\u00e1n. A DeepSpeech most 22-szer kevesebb mem\u00f3ri\u00e1t haszn\u00e1l \u00e9s 500-szor gyorsabban indul.\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=\"A Mozilla bemutatta a 0.6-os DeepSpeech besz\u00e9dfelismer\u0151 motorj\u00e1t\" src=\"\/wp-content\/uploads\/2019\/12\/113ef11374da37383391cc886c488741.png\" style=\"display:block;margin: 0 auto;\" \/><\/a><\/noindex><\/center><\/p>\n<li class=\"l\"> A nyelvi modellen ritka szavak kisz\u0171r\u00e9s\u00e9t v\u00e9gezt\u00e9k. Az \u00f6sszes sz\u00f3 sz\u00e1ma 500 ezer legn\u00e9pszer\u0171bb sz\u00f3ra cs\u00f6kkent, amelyek a modell tan\u00edt\u00e1s\u00e1hoz felhaszn\u00e1lt sz\u00f6vegben el\u0151fordultak. A v\u00e9grehajtott tiszt\u00edt\u00e1s lehet\u0151v\u00e9 tette a nyelvi modell m\u00e9ret\u00e9nek cs\u00f6kkent\u00e9s\u00e9t 1800 MB-r\u00f3l 900 MB-ra, gyakorlatilag nem befoly\u00e1solva a besz\u00e9dfelismer\u00e9s hibaszintj\u00e9t.\n<li class=\"l\"> T\u00e1mogat\u00e1s ker\u00fclt hozz\u00e1ad\u00e1sra a k\u00fcl\u00f6nb\u00f6z\u0151 <noindex><a rel=\"nofollow\" href=\"https:\/\/github.com\/mozilla\/DeepSpeech\/commit\/58fdd55eea951dabd91a1158207f2228d745e657\">technik\u00e1khoz<\/a><\/noindex> a hangadatok tov\u00e1bbi vari\u00e1ci\u00f3inak (augmentation) l\u00e9trehoz\u00e1s\u00e1hoz, amelyeket a tanul\u00e1s sor\u00e1n haszn\u00e1ltak (p\u00e9ld\u00e1ul olyan vari\u00e1ci\u00f3k hozz\u00e1ad\u00e1sa a k\u00e9szlethez, amelyek torz\u00edt\u00e1ssal vagy zajjal \u00e9rkeztek).\n<li class=\"l\"> Hozz\u00e1adtak egy k\u00f6nyvt\u00e1rat .NET platformon alapul\u00f3 alkalmaz\u00e1sok integr\u00e1l\u00e1s\u00e1hoz.\n<li class=\"l\"> \u00c1tdolgozt\u00e1k a dokument\u00e1ci\u00f3t, amely mostant\u00f3l egy k\u00fcl\u00f6n weboldalon tal\u00e1lhat\u00f3. <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>Forr\u00e1s: <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 5.0.3 - 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\/hu\/blog\/news\/kompaniya-mozilla-predstavila-dvizhok-raspoznavaniya-rechi-deepspeech-0-6\" \/>\n\t\t<meta name=\"generator\" content=\"All in One SEO (AIOSEO) 5.0.3\" \/>\n\t\t<meta property=\"og:locale\" content=\"hu_HU\" \/>\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\/hu\/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\udd47 A Mozilla bemutatta a DeepSpeech 0.6 besz\u00e9dfelismer\u0151 motort | ProHoster","description":"A Mozilla \u00e1ltal fejlesztett besz\u00e9dfelismer\u0151 motor kiad\u00e1sra ker\u00fclt.","canonical_url":"https:\/\/prohoster.info\/hu\/blog\/news\/kompaniya-mozilla-predstavila-dvizhok-raspoznavaniya-rechi-deepspeech-0-6","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":""},"schema":null,"og:locale":"hu_HU","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\/hu\/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\/hu\/wp-json\/wp\/v2\/posts\/53722","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/comments?post=53722"}],"version-history":[{"count":0,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/posts\/53722\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/media\/53723"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/media?parent=53722"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/categories?post=53722"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/tags?post=53722"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}