NVIDIA is the global leader in AI computing. NVIDIA NeMo is a conversational AI toolkit built for researchers working on automatic speech recognition (ASR), text-to-speech synthesis (TTS), large language models (LLMs), and natural language processing (NLP). NeMo's primary objective is to help researchers from industry and academia reuse prior work (code and pretrained models), making it easier to create new conversational AI models.

In partnership with Intron, NVIDIA seeks to contribute to the advancement of African clinical speech recognition through the AfriSpeech project and has provided a wealth of resources to participants for training high-performing ASR models including pretrained ASR models and the NeMo ASR toolkit.

GTC 2023 Spring Sessions

• NeMo Toolkit: Speech Training at Scale

Technical Blogs

• Get Started With NVIDIA NeMo Framework
• Accelerating Conversational AI Research with New Cutting-Edge Neural Networks and Features from NeMo 1.0
• Speeding Up Development of Speech and Language Models with NVIDIA NeMo

Pretrained Models

• Conformer CTC Large
• Conformer Transducer Large
• Conformer Transducer xLarge

Webinars

• NVIDIA NeMo: Speech Recognition, Speech Synthesis, and NLP Updates
• NVIDIA Emerging Chapters Education Series - Introduction to Building Conversational AI Applications

Get access to even more NVIDIA AI resources by joining the NVIDIA developer community at https://developer.nvidia.com/ and get access to an amazing collection of training resources at the NVIDIA Deep Learning Institute https://www.nvidia.com/en-us/training/