• Support for 70+ languages
• Trained pipelines for different languages and tasks
• Multi-task learning with pretrained transformers like BERT
• Support for pretrained word vectors and embeddings
• State-of-the-art speed
• Production-ready training system
• Linguistically-motivated tokenization
• Components for named entity recognition, part-of-speech-tagging, dependency parsing, sentence segmentation, text classification, lemmatization, morphological analysis, entity linking and more
• Easily extensible with custom components and attributes
• Support for custom models in PyTorch, TensorFlow and other frameworks
• Built in visualizers for syntax and NER
• Easy model packaging, deployment and workflow management
• Robust, rigorously evaluated accuracy

📖 For more details, see the facts, figures and benchmarks.

For detailed installation instructions, see the documentation.

• Operating system: macOS / OS X · Linux · Windows (Cygwin, MinGW, Visual Studio)
• Python version: Python >=3.7, <3.13 (only 64 bit)
• Package managers: pip · conda (via conda-forge)

Using pip, spaCy releases are available as source packages and binary wheels. Before you install spaCy and its dependencies, make sure that your pip, setuptools and wheel are up to date.

pip install -U pip setuptools wheel
pip install spacy

To install additional data tables for lemmatization and normalization you can run pip install spacy[lookups] or install spacy-lookups-data separately. The lookups package is needed to create blank models with lemmatization data, and to lemmatize in languages that don't yet come with pretrained models and aren't powered by third-party libraries.

When using pip it is generally recommended to install packages in a virtual environment to avoid modifying system state:

python -m venv .env
source .env/bin/activate
pip install -U pip setuptools wheel
pip install spacy

You can also install spaCy from conda via the conda-forge channel. For the feedstock including the build recipe and configuration, check out this repository.

conda install -c conda-forge spacy

Some updates to spaCy may require downloading new statistical models. If you're running spaCy v2.0 or higher, you can use the validate command to check if your installed models are compatible and if not, print details on how to update them:

pip install -U spacy
python -m spacy validate

If you've trained your own models, keep in mind that your training and runtime inputs must match. After updating spaCy, we recommend retraining your models with the new version.

📖 For details on upgrading from spaCy 2.x to spaCy 3.x, see the migration guide.

Trained pipelines for spaCy can be installed as Python packages. This means that they're a component of your application, just like any other module. Models can be installed using spaCy's download command, or manually by pointing pip to a path or URL.

# Download best-matching version of specific model for your spaCy installation
python -m spacy download en_core_web_sm

# pip install .tar.gz archive or .whl from path or URL
pip install /Users/you/en_core_web_sm-3.0.0.tar.gz
pip install /Users/you/en_core_web_sm-3.0.0-py3-none-any.whl
pip install https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.0.0/en_core_web_sm-3.0.0.tar.gz

import spacy
nlp = spacy.load("en_core_web_sm")
doc = nlp("This is a sentence.")

import spacy
import en_core_web_sm

nlp = en_core_web_sm.load()
doc = nlp("This is a sentence.")

git clone https://github.com/explosion/spaCy
cd spaCy

python -m venv .env
source .env/bin/activate

# make sure you are using the latest pip
python -m pip install -U pip setuptools wheel

pip install -r requirements.txt
pip install --no-build-isolation --editable .

pip install --no-build-isolation --editable .[lookups,cuda102]

pip install -r requirements.txt
python -m pytest --pyargs spacy