Monday, April 12, 2021

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

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.

NVIDIA Maxine is a GPU-accelerated artificial intelligence/machine learning (AI/ML) SDK for building virtual collaboration and content creation solutions, including video conferencing and streaming applications.

The SDK supports application features such as AI face codec, eye contact, super resolution, noise and removal. It can be combines with NVIDIA Jarvis add language-based capabilities such as transcription, translation and virtual assistants.

No comments:

Post a Comment