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.
- Speech processing
- Automatic Speech recognition (ASR): Jasper, QuartzNet, CitriNet, Conformer
- Speech Classification: MatchboxNet (command recognition), MarbleNet (voice activity detection)
- Speaker Recognition: SpeakerNet
- Speaker Diarization: MarbleNet + SpeakerNet
- NGC collection of pre-trained speech processing models.
- Natural Language Processing
- Compatible with Hugging Face Transformers and NVIDIA Megatron
- Neural Machine Translation (NMT)
- Punctuation and Capitalization
- Token classification (named entity recognition)
- Text classification
- Joint Intent and Slot Classification
- BERT pre-training
- Question answering
- GLUE benchmark
- Information retrieval
- NGC collection of pre-trained NLP models.
- Speech synthesis (TTS)
- Spectrogram generation: Tacotron2, GlowTTS, FastSpeech2, FastPitch,
- Vocoders: WaveGlow, SqueezeWave, UniGlow, MelGAN, HiFiGAN
- End-to-end speech generation: FastPitch_HifiGan_E2E, FastSpeech2_HifiGan_E2E
- NGC collection of pre-trained TTS models.
Built for speed, NeMo can utilize NVIDIA's Tensor Cores and scale out training to multiple GPUs and multiple nodes.
- Python 3.6, 3.7 or 3.8
- Pytorch 1.8.1 or above
- NVIDIA GPU for training
Version | Status | Description |
---|---|---|
Latest | Documentation of the latest (i.e. main) branch. | |
Next | Documentation of the most recent release: v1.0.2 | |
Stable | Documentation of the stable (i.e. stable) branch. |
A great way to start with NeMo is by checking one of our tutorials.
FAQ can be found on NeMo's Discussions board. You are welcome to ask questions or start discussions there.
Use this installation mode if you want the latest released version.
apt-get update && apt-get install -y libsndfile1 ffmpeg
pip install Cython
pip install nemo_toolkit['all']
Use this installation mode if you want the a version from particular GitHub branch (e.g main).
apt-get update && apt-get install -y libsndfile1 ffmpeg
pip install Cython
python -m pip install git+https://github.com/NVIDIA/NeMo.git@{BRANCH}#egg=nemo_toolkit[all]
Use this installation mode if you are contributing to NeMo.
apt-get update && apt-get install -y libsndfile1 ffmpeg
git clone https://github.com/NVIDIA/NeMo
cd NeMo
./reinstall.sh
If you chose to work with main branch, we recommend using NVIDIA's PyTorch container version 21.03-py3 and then installing from GitHub.
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:21.03-py3
Many example can be found under "Examples" folder.
We welcome community contributions! Please refer to the CONTRIBUTING.md CONTRIBUTING.md for the process.
NeMo is under Apache 2.0 license.