Ci bi mu melGis bi ci topp
Architecture konformer
Audio IA
GUIDE IA Audio
Architecture de parole
DeepSpeech xeetu xàmmee kàddu la bu Baidu dugal ci 2014, muy màndargaal man-mani audio yu ñor yi ci mbind mi, di jëfandikoo reso neuronal buy baaxoo tàggat ak ñàkkum CTC.
Déglul tegtal biiIA-nettali · ~2 min
Ci xët wii2 simili jàng
Résumé
Jàppale na ñu njëkka joge ci pipeline ASR yu jafee defar, ñu dem ci sistem yuñ jàng te lalu ci done.
Plongeur bu xóot
Xammekaayu kàddu yu yàgg yi dañu boole ay xeeti akustik yu wuute, diksoneer waxin, ak xeeti làkk yu am cër yuñ defaree loxo. DeepSpeech dafa wecci li ëpp ci loolu ak benn reso neuronal buñ tàggat ba ci njeexte li. Architecture bi dafay jël spectrogram wala MFCC ci kaw kadre audio yu gàtt ba noppi di leen dundal ci ay couche yu bari yuñ boole, couche buy baamtu ci ñaari yoon yuy jàpp contexte ci jamono yu weesu ak ëlëg, ak couche buy génne distribution probabilité ci kaw araf yi ci jéego bu nekk. Li gëna am solo mooy, dafay jëfandikoo Classification Temporal Connectionist (CTC), muy may reso bi mu jàng liggéey bi am ci diggante audio ak mbind te soxlawul etiketu kadre. Ginaaw loolu Mozilla genne ab jëfandikoo open-source bu siiw (ak yeneen yu bees yuy jëfandikoo jëmmal bu lalu ci LSTM, jëmmal ci streaming), muy tax jëfandikoo gi gëna yomba jëfandikoo.
Doxal ci àdduna dëgg
Offline, ci aparey biy xàmmee ndigalu baat ngir aplikaasioŋ yiñ jagleel kumpa, di jëfandikoo DeepSpeech bu Mozilla
Defar ay projet de transcription ci ay podcast wala ay diskur te doo yéem ci ab serwiisu cloud
Jàngale li gëna am solo ci ASR ak CTC ci njàngum masin ci daara yu kawe yi
Tabax interfaasu baat buñ personaalise bu IoT wala aparey yuñ samp fu ñu soxla xàmmeekaay bu woyof te mëna streaming
Ëlëgu architecture DeepSpeech
DeepSpeech ci boppam ñu ngi ko wecci bu baax ci arsitektir yu lalu ci bàyyi xel ak soppi (Conformer, Whisper, wav2vec 2.0) yuy jàpp muy lu gëna gudd te di saytu seen bopp ci audio bu amul etiket. Waaye xalaatam yu am solo yi, tàggat ci njeexte ak dekodaas CTC, ñu ngi des ci fundamental te ba leegi ñu ngi feeñ ci biir sistem hybrid yu bees yi. Legacy bi ci konseptioŋ la: dafa firndeel ni benn model buñ jàng mën na xëcc ay pipeline yuñ defar bu baax, loolu moo ubbi buntu model yu yaatu yu tay yi, lakk yu bari, yu ñuy saytu seen bopp.
Teg ko ci jëf
Lu tax mu am solo
- Dugg ak yegg. Dafay gëna yombal jëfandikoo gi jaaraleko ci transkripsioŋ, nettali ak interfaasu baat.
- Njëgg ak budget. Ekipu mejaa yi mën nañu yónnee audio bu leer ci anam wu gëna gaaw te seen xaalis gëna néew.
- Gaawaay ak yaatuwaay. Sistem yiy jàkkarloo ak kiliyaan bi mën nañu def waxtaan ci anam wu gëna yaatu.
Moytul
- Jëfandikoo baat ci anam wu jaarul yoon ak niru ak nit dafay gëna yokk sudee nanguwul.
- Jaar-jaar mën na wàññeeku ci aksan yi, dialect yi wala barab yu bari xumbaay.
- Audio synthetik mën nañu ko jaawale ak wax ju dëggu sudee amul etiket bu leer.
Jéego yi ci topp
- Wutal ndigal bu leer ngir jàpp baat bi, klone ko ak jëfandikoowaat ko.
- Saytu kalite ci kàddukat yu bari ak anam yu bari ci ginaaw.
- Mandargal kañ la nit wara xoolaat wala nangu ay génne.
- Etiketu audio synthetik te nga denc dokimaa ci fimu bawoo ngir mëna lim.
Weyal di banneexu
Bulletin bu amul fayda
Jàngal xibaar AI bu bes
Ñatti jaar-jaari IA yuñ firndeel bis bu nekk ci ayu-bis bi, ñu bind leen ci Àngle bu leer. Gratis ba fàww, amul yëgle.
Benn email bis bu nekk ci ayu-bis bi. Benn klik nga dindi abonemaa bi. Dunu musa jaay wala séddoo sa adres.
Nattal sa bopp
Take the DeepSpeech Architecture quiz
Feedback ci saasi ci bépp tontu, ak sertifikaa buñ mëna séddoo ak ID buñ mëna saytu soo jàllee ci njàng mi.
Jàppale njàngum IA te doo fay. AI Understanding mbootaay la buy def te Yàlla tax — amul yëgle, amul paywall, musul am. Defal ab sarax
Laaj yi ñuy faral di laaj
Luy Architecture DeepSpeech?
DeepSpeech xeetu xàmmee kàddu la bu Baidu dugal ci 2014, muy màndargaal man-mani audio yu ñor yi ci mbind mi, di jëfandikoo reso neuronal buy baaxoo tàggat ak ñàkkum CTC. Jàppale na ñu njëkka joge ci pipeline ASR yu jafee defar, ñu dem ci sistem yuñ jàng te lalu ci done.
Ban fonction perte mooy may DeepSpeech mu tàggat te du am niveau de cadre ci digganté audio ak text?
CTC dafay dugal ab màndarga bu amul dara ba noppi boole ci kaw bépp yoon bu baax buy wàcci ci bind biñ bëgga, dindi soxla etiketu kaadar bu nekk.
Lan mooy filosofi architecture bi DeepSpeech siiwal?
DeepSpeech moo wecci pipeline bi fi yàgg a nekk, mu am benn reso neuronal buñ tàggat, muy coppite bu am solo ci jëmmal ASR.
Lu tax DeepSpeech di jëfandikoo ab layer buy dellusi ci ñaari yoon?
RNN bidirectional dafay doxal toppalante bi ci ñaari yoon yi, kon génne bu nekk dafay am njariñ ci contexte akustik bi ko wër, gëna dëgëral njub.
Ban xeetu man-mani dugal la DeepSpeech di faral di doxalee?
Modèle bi dafay jëfandikoo man-mani audio yu tollu ci niveau cadre lu ci melni spectrogram wala MFCC ba noppi di génne ay probabilite ci jéego bu nekk.
Lan lañuy faral di yokk ci waxtu dekode ngir gëna baaxal tànneefi baat yi ak ortograafi DeepSpeech?
Soo boolee génnug akustik bi ak xeetu làkk wi ci biti ci diiru dekodaas bi, dafay jàppale sistem bi mu defar kàddu yu gëna neexa dégg ak ortograafi.
Weyal di jàng
Gid yu jëm ci loolu
Tann nañu yeneen njiit ngir topic bii