NVIDIA Jarvis: Speech Recognition, Real-Time Machine Translation, and Controllable Text-to-Speech

  Weergaven 3,036

NVIDIA

24 dagen geleden

NVIDIA Jarvis is a framework for building multimodal conversational AI apps with state-of-the-art models optimized to run in real time. Watch to see Jarvis' automatic speech recognition (ASR) accuracy when fine-tuned on medical jargon, its real-time neural machine translation from English to Spanish and Japanese, and its powerful controllability of neural text-to-speech.

Reacties
Automatic Speech Recognition - An Overview
1:24:41
Microsoft Research
Weergaven 85K
ITZY "마.피.아. In the morning" M/V
3:05
JYP Entertainment
Weergaven 68 mln.
Christian Horner's tour of our new Engineering 'Treehouse'
2:31
But how does bitcoin actually work?
26:21
3Blue1Brown
Weergaven 9 mln.
Speech recognition Python and Asterisk
13:49
Angel Geraldo Tech
Weergaven 1,9K
State-of-the-Art in Speech Technologies
31:23
Microsoft Research
Weergaven 3,1K
Serenade: JavaScript Voice Coding
01:21
ITZY "마.피.아. In the morning" M/V
3:05
JYP Entertainment
Weergaven 68 mln.
Christian Horner's tour of our new Engineering 'Treehouse'
2:31
I wasted $1000 on MYSTERY TECH!
21:01
Austin Evans
Weergaven 768K
Building his PC went HORRIBLY wrong
18:51
The Largest Sandcastle Ever Built
3:24
Daily Dose Of Internet
Weergaven 4,9 mln.