Ubuyobozi bwa Audio AI

EnCodec Ijwi Ryerekana

EnCodec ni __AIU_PROTECTED_13 __ 'kwizerwa cyane kwijwi ryamajwi ya codec yerekana imvugo numuziki kuri bitrate nkeya cyane hamwe nubwiza burwanya imiterere iremereye cyane.

2 min somaIbiherutse kuvugururwa

Incamake

It matters because it underpins modern generative audio systems and ships in open-source form for anyone to use.

Kwibira cyane

Yarekuwe na Meta AI mu 2022, EnCodec ikurikira igishushanyo mbonera cya SoundStream ya encoder, ibisigisigi bya vector bisigaye (RVQ), hamwe na decoder yatojwe kurangiza, ariko ikongeramo byinshi binonosoye. Ikoresha uburyo-busobekeranye bwa kodegisi ya kodegisi, ibipimo byinshi bya spekrogramu hamwe nigihe-cyo gutakaza ibyangiritse, hamwe nivangura rirwanya ubuziranenge. Umusanzu ugaragara ni moderi ntoya ya Transformer ishingiye kuri entropiya yerekana irushijeho gukanda kode igereranijwe nta gihombo, ikuramo bits ziyongereye nta gihombo cyiza. EnCodec irashiraho kandi iringaniza ihita ipima igihombo kinini cyamahugurwa ahiganwa kugirango bakomeze gushikama. Ikora 24 kHz monophonic na 48 kHz amajwi ya stereo, ikora kuri bitrate nka 1.5, 3, 6, na 12 kbps, naho kuri 6 kbps igera mubwiza ugereranije na MP3 kuri 64 kbps. Ibimenyetso byayo imbaraga __AIU_PROTECTED_13 __ 'MusicGen na AudioGen.

Ubushishozi

EnCodec ya kodegisi yerekana urugero rwumurongo hamwe no guhindagurika muburyo bukurikiranye, RVQ ihinduka mubice byerekana codebook. Ururimi rworoheje rwimvugo rwerekana imiterere yibi bimenyetso hamwe na arithmetic-code yabyo, igarura iyindi compression kubuntu. Imyitozo iringaniza ikuraho imisanzu igenda ituruka ku kwiyubaka, kwerekanwa, no gutakaza igihombo ku buryo nta jambo rimwe ryiganje, ibyo bigatuma imyitozo yibikorwa byinshi ihamye murwego rwa bitrate yuzuye.

Ingaruka z'Ingamba

Kugera no kugera

Itezimbere kugerwaho binyuze mu kwandukura, kuvuga, no guhuza amajwi.

Igiciro na bije

Amatsinda yibitangazamakuru arashobora kohereza amajwi yihuse hamwe na bije nto.

Umuvuduko n'igipimo

Sisitemu ireba abakiriya irashobora gutunganya imikoranire ivugwa murwego runini.

Kazoza ka EnCodec Ijwi Ryerekana

EnCodec isanzwe yerekana ibimenyetso byerekana amajwi menshi afungura amajwi, kandi abayikomokaho barimo gusunika ubudahemuka kuri bitrate yo hasi, stereo yuzuye hamwe nu rwego rwo kongera kwiyubaka, hamwe no guhuza imbaraga hamwe n’inyandiko-ku-majwi hamwe n’umwandiko-ku-muzika. Tegereza kwaguka kwagutse mu itumanaho rito, itumanaho-nyaryo, kandi nkurwego rusanzwe 'amajwi token' urwego rutuma ururimi runini-rwerekana imiterere yububiko rusoma kandi rwandika amajwi.

Gushyira mu bikorwa Isi

Tokenizing amajwi ya __AIU_PROTECTED_13 __ 'UmuzikiGen na AudioGen inyandiko-y-amajwi

Gucomeka imvugo ya 24 kHz kuri 1.5-6 kbps yo kwaguka kwagutse

Encoding ya 48 kHz umuziki wa stereo hamwe nubwiza hafi ya MP3 kuri bitrate yo hejuru cyane

Gukora nkisoko ifunguye-codec yubushakashatsi hamwe n'amajwi ya ML binyuze kuri bariyeri yasohotse

Ingaruka & Kurinda

Gukoresha nabi amajwi no kwigira ibyago byiyongera mugihe uruhushya rubuze.

Ukuri kurashobora kugabanuka hejuru yimvugo, imvugo, cyangwa urusaku rwibidukikije.

Amajwi yubukorikori arashobora kwibeshya kumvugo yukuri nta kirango gisobanutse.

Igishushanyo mbonera

1

Shaka uruhushya rusobanutse rwo gufata amajwi, gukoroniza, no gukoresha.

2

Ikizamini cyiza mubiganiro bitandukanye hamwe nuburyo bwimbere.

3

Sobanura igihe umuntu agomba gusuzuma cyangwa kwemeza ibisubizo.

4

Andika amajwi yubukorikori kandi ugumane inyandiko zerekana kubazwa.

Komeza Ubushakashatsi

Free newsletter

Get the daily AI briefing

Three verified AI stories every weekday morning, written in plain English. Free forever, no ads.

One email each weekday. Unsubscribe in one click. We never sell or share your address.

Test yourself

Take the EnCodec Audio Compression quiz

Instant feedback on every answer, and a shareable certificate with a verifiable ID once you pass a course.

Tangira ikibazo

Support free AI education. AI Understanding is a 501(c)(3) nonprofit — no ads, no paywall, ever. Make a donation

Ubuyobozi bukurikira

Kwinjiza Amajwi no Kwiga Guhagararira

Ibibazo bikunze kubazwa

What is EnCodec Audio Compression?

EnCodec ni __AIU_PROTECTED_13 __ 'kwizerwa cyane kwijwi ryamajwi ya codec yerekana imvugo numuziki kuri bitrate nkeya cyane hamwe nubwiza burwanya imiterere iremereye cyane. Nibyingenzi kuko bishimangira sisitemu yamajwi yerekana amajwi hamwe nubwato muburyo bwugururiwe isoko kugirango umuntu wese akoreshe.

Nuwuhe muryango wasohoye EnCodec?

EnCodec yatangijwe na Meta AI (FAIR) mu 2022 nka codec ya majwi yizerwa cyane.

Niki kintu cyinyongera EnCodec yongeramo kubura gutakaza compression nyinshi kuva mubimenyetso byayo?

EnCodec itoza Transformer ntoya yo guhanura ibimenyetso byerekana ibimenyetso hamwe na arithmetic-code yabyo, igera kuri compression itagira igihombo hejuru ya RVQ.

Hafi ya 6 kbps, ubuziranenge bwa EnCodec bwavuzwe ko bugereranywa na MP3 kuri bitrate?

EnCodec kuri 6 kbps igera kumiterere yibintu bisa na MP3 kuri 64 kbps, inyungu nini.

Ni ikihe kibazo 'balancer' ya EnCodec ikemura mugihe cy'amahugurwa?

Hamwe nigihombo kinini (kwiyubaka, kwerekanwa, guhangana), kuringaniza ikuraho gradients zabo kuburyo ntampamvu nimwe yiganje, guhagarika amahugurwa.

Ni ubuhe buryo bwibanze bwo kubara EnCodec isangira na SoundStream?

Kimwe na SoundStream, EnCodec ikoresha umubare wibisigisigi bya vector kugirango isobanure neza kodegisi yerekana indangagaciro za codebook.