NeMo is a toolkit for creating Conversational AI applications.
NeMo toolkit makes it possible for researchers to easily compose complex neural network architectures for conversational AI using reusable components - Neural Modules. Neural Modules are 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.
The toolkit comes with extendable collections of pre-built modules and ready-to-use models for:
- Automatic Speech Recognition (ASR)
- Natural Language Processing (NLP)
- Speech synthesis, or Text-To-Speech (TTS)
Built for speed, NeMo can utilize NVIDIA's Tensor Cores and scale out training to multiple GPUs and multiple nodes.
NeMo's works with:
- Python 3.6 or 3.7
- Pytorch 1.6 or above
The easiest way to start training with NeMo is by using NeMo's container.
It has all requirements and NeMo 1.0.0b2 already installed.
docker run --gpus all -it --rm -v <nemo_github_folder>:/NeMo --shm-size=8g \
-p 8888:8888 -p 6006:6006 --ulimit memlock=-1 --ulimit \
stack=67108864 --device=/dev/snd nvcr.io/nvidia/nemo:1.0.0b3If you chose to work with main branch, we recommend using NVIDIA's PyTorch container version 20.09-py3.
docker run --gpus all -it --rm -v <nemo_github_folder>:/NeMo --shm-size=8g \
-p 8888:8888 -p 6006:6006 --ulimit memlock=-1 --ulimit \
stack=67108864 --device=/dev/snd nvcr.io/nvidia/pytorch:20.09-py3If you are not inside the NVIDIA docker container, please install Cython first. If you wish to either use the ASR or TTS collection, please install libsndfile1 and ffmpeg as well.
pip install Cythonapt-get update && apt-get install -y libsndfile1 ffmpeg(If you want to install the TTS or ASR collections)
Once requirements are satisfied, simply install using pip:
pip install nemo_toolkit[all]==1.0.0b2(latest version)
Or if you want the latest (or particular) version from GitHub:
python -m pip install git+https://github.com/NVIDIA/NeMo.git@{BRANCH}#egg=nemo_toolkit[all]- where {BRANCH} should be replaced with the branch you want. This is recommended route if you are testing out the latest WIP version of NeMo - installing in release mode../reinstall.sh- from NeMo's git root. This will by default install the version from the current branch in development mode. To change to release mode pass 'release'.
<nemo_github_folder>/examples/ folder contains various example scripts. Many of them look very similar and have the same arguments because
we used Facebook's Hydra for configuration.
Here is an example command which trains ASR model (QuartzNet15x5) on LibriSpeech, using 4 GPUs and mixed precision training. (It assumes you are inside the container with NeMo installed)
root@987b39669a7e:/NeMo# python examples/asr/speech_to_text.py --config-name=quartznet_15x5 \
model.train_ds.manifest_filepath=<PATH_TO_DATA>/librispeech-train-all.json \
model.validation_ds.manifest_filepath=<PATH_TO_DATA>/librispeech-dev-other.json \
trainer.gpus=4 trainer.max_epochs=128 model.train_ds.batch_size=64 \
+trainer.precision=16 +trainer.amp_level=O1 \
+model.validation_ds.num_workers=16 \
+model.train_ds.num_workers=16 \
+model.train_ds.pin_memory=True
#(Optional) Tensorboard:
tensorboard --bind_all --logdir nemo_experiments| Version | Status | Description |
|---|---|---|
| Latest | Documentation of the latest (i.e. main) branch | |
| Stable | Documentation of the stable (i.e. 0.11.1) branch | |
| Main | Documentation of the main branch | |
| v0.11.1 | Documentation of the v0.11.1 release | |
| v0.11.0 | Documentation of the v0.11.0 release |
The best way to get started with NeMo is to checkout one of our tutorials.
Most NeMo tutorials can be run on Google's Colab.
To run tutorials:
- Click on Colab link (see table below)
- Connect to an instance with a GPU (Runtime -> Change runtime type -> select "GPU" for hardware accelerator)
| Domain | Title | GitHub URL |
|---|---|---|
| NeMo | Simple Application with NeMo | Voice swap app |
| NeMo | Exploring NeMo Fundamentals | NeMo primer |
| NeMo Models | Exploring NeMo Model Construction | NeMo models |
| ASR | ASR with NeMo | ASR with NeMo |
| ASR | Speech Commands | Speech commands |
| ASR | Speaker Recognition and Verification | Speaker Recognition and Verification |
| ASR | Online Noise Augmentation | Online noise augmentation |
| ASR | Beam Search and External Language Model Rescoring | Beam search and external language model rescoring |
| NLP | Using Pretrained Language Models for Downstream Tasks | Pretrained language models for downstream tasks |
| NLP | Exploring NeMo NLP Tokenizers | NLP tokenizers |
| NLP | Text Classification (Sentiment Analysis) with BERT | Text Classification (Sentiment Analysis) |
| NLP | Question answering with SQuAD | Question answering Squad |
| NLP | Token Classification (Named Entity Recognition) | Token classification: named entity recognition |
| NLP | Joint Intent Classification and Slot Filling | Joint Intent and Slot Classification |
| NLP | GLUE Benchmark | GLUE benchmark |
| NLP | Punctuation and Capitialization | Punctuation and capitalization |
| NLP | Named Entity Recognition - BioMegatron | Named Entity Recognition - BioMegatron |
| NLP | Relation Extraction - BioMegatron | Relation Extraction - BioMegatron |
| TTS | Speech Synthesis | TTS inference |
| Tools | CTC Segmentation | CTC Segmentation |
| Tools | Text Normalization for Text To Speech | Text Normalization |
We welcome community contributions! Please refer to the CONTRIBUTING.md for the process.
NeMo is under Apache 2.0 license.