NVIDIA Canary
STT.ai ma socoto noocan — boggani waa macluumaad ku saabsan ka soo horjeeda.
La socodsiiya oo leh moodooyinka aan ku socdaan →
3.5%
WER
4
Afaf
45.0x
Xawaaraha
CC-BY-4.0
Liisan
_Qormo NVIDIA Canary
NVIDIA Canary waa 1B parameter oo ku fiican in Ingiriisi, Jarmalka, Faransiiska, iyo Spanish. Built on the NeMo framework, wuxuu isticmaalaa FastConformer encoder la decoder transformer iyo taageero u aqoonsiga luqadda otomaatig ah iyo turjumaad.
Macluumaad qaabka
- BixiyeNVIDIA
- Naqshadeynta-
- LiisanCC-BY-4.0
- La cusbooneysiiyayMar 2026
Su'aalaha badanaa la isweydiiyo
NVIDIA Canary waa hadal-to-text qaabka by NVIDIA. STT.ai hadda ma socoto NVIDIA Canary — boggani waa macluumaad ku saabsan qaabka. Si loo qoro on STT.ai, qaabka dooranaya wuxuu bixiyaa qoyska Whisper (Turbo, Large V3, Dheer, yar).
On tirakoobyada caadiga ah, NVIDIA Canary gaadhay in ka badan 3.5% Word Error Rate. Real-world saxnaanta ku xiran tahay tayada audio, afka, iyo afka; in ay maqal ah ama afka, ka fikiraan boqolkiiba dhibcood yar oo ka sareeya WER.
NVIDIA Canary ma aha mid la heli karo STT.ai. Sharciyada liisankiisa ayaa maamula inuu ku socdo adiga. STT.ai's free tier covers the Whisper models we do run - 600 daqiiqo si ay u bilaabaan, ka dibna bishii bilaash ah oo bilaash ah.
NVIDIA Canary waxaa lagu soo saaray hoos CC-BY-4.0, a permissive license furan-source. Waxaad awoodi kartaa self-host NVIDIA Canary on your hardware ama isticmaali version our martida — labadaba waa ganacsi loo isticmaali karo.
NVIDIA Canary taageeraa 4 luqadood. Auto-ka-qabashada doorata luqadda saxda ah ee audio ugu badan; waxaad sidoo kale ku qeexi kartaa gacanta si ay u qaado saxnaanta yar.
NVIDIA Canary audio ku saabsan 45.0x waqti dhab ah on our GPUs. A 1-saac file audio dhamaystiran hoos 1 daqiiqo; files dheeri ah oo fariin email ah marka la sameeyo.
NVIDIA Canary waxaa ku jira 1B parameters. Models weyn u badan tahay in ay ka sii sax ah laakiin ka sii dhakhso badan; STT.ai martida NVIDIA Canary on GPU sidaas darteed tirada parameter ma saameyn ku yeelan doontaa shaqadaaga dhinac macaamiisha.
NVIDIA Canary aqbalaa qaab kasta oo STT.ai taageeraya — MP3, WAV, M4A, FLAC, OGG, MP4, MKV, MOV, WebM, AVI, iyo kuwa kale. soo saarka sida TXT, SRT, VTT, DOCX, JSON, ama PDF.
Haa. Speaker diarization la socda NVIDIA Canary oo ku saabsan qoraal kasta — hadal kasta oo waxaa lagu calaamadiyay oo waxaad ku bedeli kartaa magacooda editor ka dib.
Haa. NVIDIA Canary ku socda deegaankayaga maamula - audio waa la xakamayn karaa oo la tirtiri karaa si default ah oo aan marnaba loo isticmaalin tababarka aan la oggolaanin. Pro qorshayaasha ku darto sirta dhinac macaamiisha ee qoraalada fadhiya.
isticmaali qalab la barbar dhigo-stt si ay u socdaan NVIDIA Canary ka hor mid ka mid ah noocyada kale ee taageeray on audio isku mid ah - waxaad arki doontaa WER, qaybta tirada, labels hadal, iyo kalsoonida dhibcaha dhinac-by-laab. The NVIDIA Canary vs Whisper Large V3 la barbardhigo waa ugu badan ee caadiga ah la socda.
Haa. Xulo "nvidia-canary" sida paramtirka moodalka ee / v1 / transcribe endpoint. Python iyo Node.js SDKs waxaa ka mid ah NVIDIA Canary tusaale. Free API tier waxaa ka mid ah 100 daqiiqo / bilood.
Waa yaabe. Sababtoo ah NVIDIA Canary waa CC-BY-4.0-licensed, waxaad awoodi kartaa inaad iska diiwaangeliso. STT.ai's open-source page liiska mashruuca repo iyo miisaanka. Kooxaha wax soo saarka badankood waxay isticmaalaan noocayaga martida ah si ay u dhaafaan GPU iibka, qaababka isbeddelka, iyo ops.