batermj / NeMo

Neural Modules: a toolkit for conversational AI

NVIDIA Neural Modules: NeMo

NeMo (Neural Modules) is a toolkit for creating AI applications using neural modules - conceptual blocks of neural networks that take typed inputs and produce typed outputs. Such modules typically represent data layers, encoders, decoders, language models, loss functions, or methods of combining activations.

NeMo makes it easy to combine and re-use these building blocks while providing a level of semantic correctness checking via its neural type system. As long as two modules have compatible inputs and outputs, it is legal to chain them together.

NeMo's API is designed to be framework-agnostic, but currently only PyTorch is supported.

NeMo follows a lazy execution model: no computation is done until an action (such as train(...) is called.

The toolkit comes with extendable collections of pre-built modules for automatic speech recognition (ASR), natural language processing (NLP) and text synthesis (TTS). Furthermore, NeMo provides built-in support for distributed training and mixed precision on the latest NVIDIA GPUs.

NeMo consists of:

• NeMo Core: fundamental building blocks for all neural models and type system.
• NeMo collections: pre-built neural modules for particular domains such as automatic speech recognition (nemo_asr), natural language processing (nemo_nlp) and text synthesis (nemo_tts).

Introduction

See this video for a quick walk-through.

Requirements

1. Python 3.6 or 3.7
2. PyTorch 1.2.* or 1.3.* with GPU support
3. (optional for best performance) NVIDIA APEX. Install from here: https://github.com/NVIDIA/apex

Getting started

THE LATEST STABLE VERSION OF NeMo is 0.8.2 (which is available via PIP).

We recommend to use NVIDIA NGC PyTorch container which already includes all the requirements above.

• Pull the docker: docker pull nvcr.io/nvidia/pytorch:19.10-py3
• Run: docker run --runtime=nvidia -it --rm -v <nemo_github_folder>:/NeMo --shm-size=2g -p 8888:8888 -p 6006:6006 --ulimit memlock=-1 --ulimit stack=67108864 nvcr.io/nvidia/pytorch:19.10-py3

pip install nemo-toolkit  # installs NeMo Core
pip install nemo-asr # installs NeMo ASR collection
pip install nemo-nlp # installs NeMo NLP collection

• DEVELOPMENT: If you'd like to use master branch and/or develop NeMo you can run "reinstall.sh" script.

Documentation

NeMo documentation

See examples/start_here to get started with the simplest example. The folder examples contains several examples to get you started with various tasks in NLP and ASR.

Tutorials

• Speech recognition
• Natural language processing

Installing From Github

If you prefer to use NeMo's latest development version (from GitHub) follow the steps below:

Note: For step 2 and 3, if you want to use NeMo in development mode, use: pip install -e . instead of pip install .

1. Clone the repository git clone https://github.com/NVIDIA/NeMo.git
2. Go to NeMo folder and install the toolkit:

cd NeMo/nemo
pip install .

3. Install the collection(s) you want.

# Install the ASR collection from collections/nemo_asr
apt-get install libsndfile1
cd NeMo/collections/nemo_asr
pip install .

# Install the NLP collection from collections/nemo_nlp
cd NeMo/collections/nemo_nlp
pip install .

Unittests

This command runs unittests:

./reinstall.sh
python -m unittest tests/*.py

Citation

If you are using NeMo please cite the following publication

@misc{nemo2019,

title={NeMo: a toolkit for building AI applications using Neural Modules}, author={Oleksii Kuchaiev and Jason Li and Huyen Nguyen and Oleksii Hrinchuk and Ryan Leary and Boris Ginsburg and Samuel Kriman and Stanislav Beliaev and Vitaly Lavrukhin and Jack Cook and Patrice Castonguay and Mariya Popova and Jocelyn Huang and Jonathan M. Cohen}, year={2019}, eprint={1909.09577}, archivePrefix={arXiv}, primaryClass={cs.LG}

}