Ci bi mu melGis bi ci topp
Speech Recognition for People with Atypical Speech
Audio IA
GUIDE IA Audio
Xamme kàddu yu am tuuti
Whisper is OpenAI’s multilingual speech-recognition model, trained with large-scale weak supervision on approximately 680,000 hours of web-collected audio.
Déglul tegtal biiIA-nettali · ~1 min
Ci xët wii1 simili jàng
Résumé
Its encoder-decoder design supports transcription, English translation, language identification, and timestamps, while accuracy varies by language, recording, and task.
Plongeur bu xóot
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.
Doxal ci àdduna dëgg
Defar ci boppam ay mbind yuñ mëna seetee ak ay mbind ngir podcast yi ak wideo YouTube
Dafay doxal aplikaasioŋu notu ndaje yiy génne ay resumé ci Zoom wala Teams audio
Tekki janoo ci làkku jàmbur ci làkku angale ngir taskati xibaar
Tabax jumtukaayi jëfandikoo gi ñuy doxalee ci baat ak dikte ngir jëfandikukat yi mënu bind
Ëlëgu xàmmee kàddu yu baat
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.
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 Whisper Speech Recognition 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
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.
Lu tollu ci ñaata waxtu ci audio lañu tàggatee Whisper?
Whisper dañu ko tàggat ci lu tollu ci 680,000 waxtu ci làkk yu bari, audio yu bari liggéey yuñ dajale ci web bi, di done yu bari te wuute lool.
Lan mooy diggante bi Whisper di xayma ci audio bu ñor bi balaa encoder bi?
Whisper dafay soppi bépp paccu audio bu 30 sikon ci spectrogram log-Mel bu am 80 chaine, bi encodeur Transformateur bi di doxalee.
Naka la benn xeetu Whisper di defee liggéey yu bari lu ci melni transkripsioŋ ak tekki làkk?
Whisper dafay am ay token yuñ jagleel ci ndoortelu decodage bi koy wax làkk wi, liggéey bi, ak ndax dafa wara génne timestamps.
Ban arsitektir neuronal la Whisper di jëfandikoo?
Whisper enkodeer-dekodeer la: enkodeer bi dafay jàng spectrogram bi, dekodeer bi dafay defar ay token bind ci anam wuy dellu ginaaw.
Lan moo waral ñu jàpp ni Whisper moo gëna am doole buñu ko méngale ak sistem ASR yu njëkk ya?
Tàggat ci audio yu bari te wuute, ci àdduna dëgg (aksan, bruit, crosstalk) moo jox Whisper doole ju génn ci boyet bi te amul tuning ci domen bu nekk.
Weyal di jàng
Gid yu jëm ci loolu
Tann nañu yeneen njiit ngir topic bii