Xiga xigaHagaha xiga
Aqoonsiga Hadalka ee Dadka Hadalka Aan Caadiga ahayn
AI Codka
HAGAHA Audio AI
Aqoonsiga Hadalka Shaqsiga
Whisper waa qaabka aqoonsiga hadalka-luqaadaha badan ee OpenAI, oo lagu tababaray ilaalin daciif ah oo baaxad weyn oo ku dhawaad 680,000 saacadood oo maqal shabakadeed ah.
Dhageyso hagahanAI-waa laga sheekeeyay · ~1 min
Boggaan1 daqiiqo akhri
Dulmar
Its encoder-decoder design supports transcription, English translation, language identification, and timestamps, while accuracy varies by language, recording, and task.
quusid qoto dheer
Introduced in 2022, Whisper is a Transformer encoder-decoder trained on approximately 680,000 hours of multilingual audio paired with transcripts or translation text collected from the web. The data is uneven across languages, and performance varies by language and task. Whisper processes audio in 30-second chunks and uses task and language tokens to select transcription, English translation, or timestamped output. Released weights and inference code are under the MIT license.
Dhaqangelinta Adduunka-dhabta ah
Si toos ah u soo saari kara qoraalada la raadin karo iyo qoraallada podcasts iyo fiidiyowyada YouTube
Awood siinta abka kulanka-noocyada tooska ah ee soo saara koobabyada Soo koobida ama Codka Kooxaha
Si toos ah ugu tarjumaadda wareysiyada luqadda ajnabiga ah qoraalka Ingiriisiga ee saxafiyiinta
Dhisidda agabka gelitaanka codka lagu xakameynayo iyo hadalka ee isticmaalayaasha aan qori karin
Mustaqbalka Aqoonsiga Hadalka Shaqsiga
Whisper’s release supports transcription and captioning applications. Real-world performance depends on language coverage, audio quality, accents, domain vocabulary, and evaluation conditions. Measure error rates on representative recordings, with human review where transcripts have consequential use.
Ku dhaqangelinta
Maxay muhiim u tahay
- Helitaanka iyo gaarsiinta. Waxay wanaajisaa marin u helida iyada oo loo marayo qoraal-qorid, sheeko, iyo is-dhexgalyo cod.
- Qiimaha iyo miisaaniyada. Kooxaha warbaahintu waxay ku soo rari karaan codka sifaysan si degdeg ah iyagoo wata miisaaniyado yaryar.
- Xawaaraha iyo miisaanka. Nidaamyada u jeedda macmiisha waxay ka baaraandegi karaan isdhexgalka hadalka si weyn.
Iska ilaali
- Si xun u isticmaalka codka iyo khataraha is-yeelyeelku way kordhaan marka oggolaanshaha la waayo.
- Saxnimadu waxay hoos ugu dhici kartaa lahjadaha, lahjadaha, ama jawiga buuqa badan.
- Maqalka synthetic waxaa lagu khaldi karaa hadal dhab ah iyada oo aan si cad loo calaamadin.
Tallaabooyinka xiga
- Hel ogolaansho cad oo ku saabsan qabashada codka, xidhitaanka, iyo dib u isticmaalka
- Tijaabi tayada ku hadasha kala duwan iyo xaaladaha asalka.
- Qeex marka bani'aadamku ay tahay inuu dib u eego ama oggolaado wax soo saarka.
- Ku calaamadee codka synthetic oo xafid diiwaannada la-xisaabtanka.
Sii wad Sahaminta
Warqad bilaash ah
Hel warbixinta maalinlaha ah ee AI
Saddex sheeko oo la xaqiijiyay oo AI ah maalin kasta oo shaqo ah, oo lagu qoray Ingiriis fudud. Bilaash had iyo jeer, aan xayaysiis lahayn.
Hal iimayl maalin kasta oo shaqo ah. Ka bax hal gujin. Marna ma iibinno ama ma wadaagno ciwaankaaga.
Is tijaabi
Take the Whisper Speech Recognition quiz
Fikrad degdeg ah oo ku saabsan jawaab kasta, iyo shahaado la wadaajin karo oo leh aqoonsi la xaqiijin karo markaad ka gudubto koorso.
Taageer waxbarashada AI bilaashka ah. AI Understanding waa 501(c)(3) aan faa'iido doon ahayn — xayaysiis la'aan, albaab lacag ah ma jiro, had iyo jeer. Samee deeq
Su'aalaha soo noqnoqda
What is Whisper Speech Recognition?
Whisper is OpenAI’s multilingual speech-recognition model, trained with large-scale weak supervision on approximately 680,000 hours of web-collected audio. Its encoder-decoder design supports transcription, English translation, language identification, and timestamps, while accuracy varies by language, recording, and task.
Qiyaastii imisa saacadood oo maqal ah ayaa lagu tababaray Whisper?
Whisper waxaa lagu tababaray ilaa 680,000 saacadood oo luuqado badan ah, maqal hawlo badan oo laga soo ururiyay shabakadda, xog aan caadi ahayn oo ballaaran oo kala duwan.
Waa maxay matalaada dhexe ee Whisper ka xisaabinaysa codka qaydhiin ka hor codeeyaha?
Whisper waxay u beddeshaa qayb kasta oo 30-ilbiriqsi ah oo maqal ah oo u beddela 80-channel log-Mel spectrogram, kaas oo Transformer-ku uu socodsiiyo.
Sidee buu hal nooc oo Whisper ah u qabtaa hawlo badan sida qorista iyo tarjumaada?
Shuruudaha ku sheekee calaamado gaar ah bilawga dejinta koodka kuwaas oo u sheegaya luqadda, hawsha, iyo haddii la sii daayo waraaqaha wakhtiga.
Waa maxay qaab dhismeedka neerfaha guud ee uu Whisper adeegsato?
Whisper waa furaha-decoder-ka-beddelaha: codeeyaha ayaa akhriya spectrogram-ka oo furaha ayaa soo saara calaamadaha qoraalka si toos ah.
Waa maxay sababta Whisper loogu tixgaliyo inay si gaar ah u adag tahay marka la barbar dhigo nidaamyada hore ee ASR?
Tababar ku saabsan tiro aad u badan oo kala duwan, maqal maqal ah oo dunida dhabta ah (lahjadaha, buuqa, iskutallaabtu) waxay siisay Whisper awood xoog leh oo ka baxsan sanduuqa iyada oo aan la hagaajin goob kasta.
Sii wad waxbarashada
Tilmaamaha la xidhiidha
Tilmaamayaal badan ayaa loo doortay mawduucan