NVIDIA NeMo is a conversational AI toolkit built for researchers working on automatic speech recognition (ASR), natural language processing (NLP), and text-to-speech synthesis (TTS). The primary objective of NeMo is to help researchers from industry and academia to reuse prior work (code and pretrained models and make it easier to create new conversational AI models. The project is based on this framework and, within the use of Rasa NLU processes, we can build and integrate components for a conversional AI. The aim of the project is to build an artificial intelligence agent to support people in specific task domains, generally the dataset of the NLU can merge, integrate and transform the supported tasks. Furthermore, we can have a chat for the trascriptions of the speeches between the agent and the customers to save a speech status in the session.
Project integrates NeMo framework with the Rasa NLU. Rasa helps you build contextual assistants capable of having layered conversations with lots of back-and-forth. In order for a human to have a meaningful exchange with a contextual assistant, the assistant needs to be able to use context to build on things that were previously discussed – Rasa enables you to build assistants that can do this in a scalable way.
The project is composed by two elements which has some setups before to start the project.
- Flask Server - for the ASR and TTS invocations
- Rasa Shell Container - for the environment on the Rasa Server
- Python 3.6, 3.7 or 3.8
- Pytorch 1.10.0 or above
- Andrea Gurioli (@andreagurioli1995)
- Giovanni Pietrucci (@giovanniPi997)
- Mario Sessa (@kode-git)