spaCy/website/docs/api/cli.md

title	teaser	source	menu
Command Line Interface	Download, train and package models, and debug spaCy	spacy/cli	Download download Link link Info info Validate validate Convert convert Train train Pretrain pretrain Init Model init-model Evaluate evaluate Package package

As of v1.7.0, spaCy comes with new command line helpers to download and link models and show useful debugging information. For a list of available commands, type spacy --help.

Download

Download models for spaCy. The downloader finds the best-matching compatible version, uses pip to download the model as a package and automatically creates a shortcut link to load the model by name. Direct downloads don't perform any compatibility checks and require the model name to be specified with its version (e.g. en_core_web_sm-2.0.0).

Downloading best practices

The download command is mostly intended as a convenient, interactive wrapper – it performs compatibility checks and prints detailed messages in case things go wrong. It's not recommended to use this command as part of an automated process. If you know which model your project needs, you should consider a direct download via pip, or uploading the model to a local PyPi installation and fetching it straight from there. This will also allow you to add it as a versioned package dependency to your project.

$ python -m spacy download [model] [--direct]

Argument	Type	Description
model	positional	Model name or shortcut (en, de, en_core_web_sm).
--direct, -d	flag	Force direct download of exact model version.
other 2.1	-	Additional installation options to be passed to pip install when installing the model package. For example, --user to install to the user home directory.
--help, -h	flag	Show help message and available arguments.
CREATES	directory, symlink	The installed model package in your site-packages directory and a shortcut link as a symlink in spacy/data.

Link

Create a shortcut link for a model, either a Python package or a local directory. This will let you load models from any location using a custom name via spacy.load().

In spaCy v1.x, you had to use the model data directory to set up a shortcut link for a local path. As of v2.0, spaCy expects all shortcut links to be loadable model packages. If you want to load a data directory, call spacy.load() or Language.from_disk() with the path, or use the package command to create a model package.

$ python -m spacy link [origin] [link_name] [--force]

Argument	Type	Description
origin	positional	Model name if package, or path to local directory.
link_name	positional	Name of the shortcut link to create.
--force, -f	flag	Force overwriting of existing link.
--help, -h	flag	Show help message and available arguments.
CREATES	symlink	A shortcut link of the given name as a symlink in spacy/data.

Info

Print information about your spaCy installation, models and local setup, and generate Markdown-formatted markup to copy-paste into GitHub issues.

$ python -m spacy info [--markdown]

$ python -m spacy info [model] [--markdown]

Argument	Type	Description
model	positional	A model, i.e. shortcut link, package name or path (optional).
--markdown, -md	flag	Print information as Markdown.
--silent, -s 2.0.12	flag	Don't print anything, just return the values.
--help, -h	flag	Show help message and available arguments.
PRINTS	stdout	Information about your spaCy installation.

Validate

Find all models installed in the current environment (both packages and shortcut links) and check whether they are compatible with the currently installed version of spaCy. Should be run after upgrading spaCy via pip install -U spacy to ensure that all installed models are can be used with the new version. The command is also useful to detect out-of-sync model links resulting from links created in different virtual environments. It will a list of models, the installed versions, the latest compatible version (if out of date) and the commands for updating.

Automated validation

You can also use the validate command as part of your build process or test suite, to ensure all models are up to date before proceeding. If incompatible models or shortcut links are found, it will return 1.

$ python -m spacy validate

Argument	Type	Description
PRINTS	stdout	Details about the compatibility of your installed models.

Convert

Convert files into spaCy's JSON format for use with the train command and other experiment management functions. The converter can be specified on the command line, or chosen based on the file extension of the input file.

$ python -m spacy convert [input_file] [output_dir] [--converter] [--n-sents]
[--morphology]

Argument	Type	Description
input_file	positional	Input file.
output_dir	positional	Output directory for converted JSON file.
converter, -c 2	option	Name of converter to use (see below).
--n-sents, -n	option	Number of sentences per document.
--morphology, -m	option	Enable appending morphology to tags.
--help, -h	flag	Show help message and available arguments.
CREATES	JSON	Data in spaCy's JSON format.

The following file format converters are available:

ID	Description
auto	Automatically pick converter based on file extension (default).
conllu, conll	Universal Dependencies .conllu or .conll format.
ner	Tab-based named entity recognition format.
iob	IOB or IOB2 named entity recognition format.

Train

Train a model. Expects data in spaCy's JSON format. On each epoch, a model will be saved out to the directory. Accuracy scores and model details will be added to a meta.json to allow packaging the model using the package command.

As of spaCy 2.1, the --no-tagger, --no-parser and --no-parser flags have been replaced by a --pipeline option, which lets you define comma-separated names of pipeline components to train. For example, --pipeline tagger,parser will only train the tagger and parser.

$ python -m spacy train [lang] [output_path] [train_path] [dev_path]
[--base-model] [--pipeline] [--vectors] [--n-iter] [--n-examples] [--use-gpu]
[--version] [--meta-path] [--init-tok2vec] [--parser-multitasks]
[--entity-multitasks] [--gold-preproc] [--noise-level] [--learn-tokens]
[--verbose]

Argument	Type	Description
lang	positional	Model language.
output_path	positional	Directory to store model in. Will be created if it doesn't exist.
train_path	positional	Location of JSON-formatted training data.
dev_path	positional	Location of JSON-formatted development data for evaluation.
--base-model, -b	option	Optional name of base model to update. Can be any loadable spaCy model.
--pipeline, -p 2.1	option	Comma-separated names of pipeline components to train. Defaults to 'tagger,parser,ner'.
--vectors, -v	option	Model to load vectors from.
--n-iter, -n	option	Number of iterations (default: 30).
--n-examples, -ns	option	Number of examples to use (defaults to 0 for all examples).
--use-gpu, -g	option	Whether to use GPU. Can be either 0, 1 or -1.
--version, -V	option	Model version. Will be written out to the model's meta.json after training.
--meta-path, -m 2	option	Optional path to model meta.json. All relevant properties like lang, pipeline and spacy_version will be overwritten.
--init-tok2vec, -t2v 2.1	option	Path to pretrained weights for the token-to-vector parts of the models. See spacy pretrain. Experimental.
--parser-multitasks, -pt	option	Side objectives for parser CNN, e.g. 'dep' or 'dep,tag'
--entity-multitasks, -et	option	Side objectives for NER CNN, e.g. 'dep' or 'dep,tag'
--noise-level, -nl	option	Float indicating the amount of corruption for data augmentation.
--gold-preproc, -G	flag	Use gold preprocessing.
--learn-tokens, -T	flag	Make parser learn gold-standard tokenization by merging ] subtokens. Typically used for languages like Chinese.
--verbose, -VV 2.0.13	flag	Show more detailed messages during training.
--help, -h	flag	Show help message and available arguments.
CREATES	model, pickle	A spaCy model on each epoch.

Environment variables for hyperparameters

spaCy lets you set hyperparameters for training via environment variables. This is useful, because it keeps the command simple and allows you to create an alias for your custom train command while still being able to easily tweak the hyperparameters. For example:

$ parser_hidden_depth=2 parser_maxout_pieces=1 spacy train [...]

### Usage with alias
alias train-parser="spacy train en /output /data /train /dev -n 1000"
parser_maxout_pieces=1 train-parser

Name	Description	Default
dropout_from	Initial dropout rate.	0.2
dropout_to	Final dropout rate.	0.2
dropout_decay	Rate of dropout change.	0.0
batch_from	Initial batch size.	1
batch_to	Final batch size.	64
batch_compound	Rate of batch size acceleration.	1.001
token_vector_width	Width of embedding tables and convolutional layers.	128
embed_size	Number of rows in embedding tables.	7500
hidden_width	Size of the parser's and NER's hidden layers.	128
learn_rate	Learning rate.	0.001
optimizer_B1	Momentum for the Adam solver.	0.9
optimizer_B2	Adagrad-momentum for the Adam solver.	0.999
optimizer_eps	Epsilon value for the Adam solver.	1e-08
L2_penalty	L2 regularization penalty.	1e-06
grad_norm_clip	Gradient L2 norm constraint.	1.0

Pretrain

Pre-train the "token to vector" (tok2vec) layer of pipeline components, using an approximate language-modeling objective. Specifically, we load pre-trained vectors, and train a component like a CNN, BiLSTM, etc to predict vectors which match the pre-trained ones. The weights are saved to a directory after each epoch. You can then pass a path to one of these pre-trained weights files to the 'spacy train' command.

This technique may be especially helpful if you have little labelled data. However, it's still quite experimental, so your mileage may vary. To load the weights back in during spacy train, you need to ensure all settings are the same between pretraining and training. The API and errors around this need some improvement.

$ python -m spacy pretrain [texts_loc] [vectors_model] [output_dir] [--width]
[--depth] [--embed-rows] [--dropout] [--seed] [--n-iter] [--use-vectors]

Argument	Type	Description
texts_loc	positional	Path to JSONL file with raw texts to learn from.
vectors_model	positional	Name or path to spaCy model with vectors to learn from.
output_dir	positional	Directory to write models to on each epoch.
--width, -cw	option	Width of CNN layers.
--depth, -cd	option	Depth of CNN layers.
--embed-rows, -er	option	Number of embedding rows.
--dropout, -d	option	Dropout rate.
--seed, -s	option	Seed for random number generators.
--n-iter, -i	option	Number of iterations to pretrain.
--use-vectors, -uv	flag	Whether to use the static vectors as input features.
CREATES	weights	The pre-trained weights that can be used to initialize spacy train.

Init Model

Create a new model directory from raw data, like word frequencies, Brown clusters and word vectors. This command is similar to the spacy model command in v1.x.

As of v2.1.0, the --freqs-loc and --clusters-loc are deprecated and have been replaced with the --jsonl-loc argument, which lets you pass in a a newline-delimited JSON (JSONL) file containing one lexical entry per line. For more details on the format, see the annotation specs.

$ python -m spacy init-model [lang] [output_dir] [--jsonl-loc] [--vectors-loc]
[--prune-vectors]

Argument	Type	Description
lang	positional	Model language ISO code, e.g. en.
output_dir	positional	Model output directory. Will be created if it doesn't exist.
--jsonl-loc, -j	option	Optional location of JSONL-formatted vocabulary file with lexical attributes.
--vectors-loc, -v	option	Optional location of vectors file. Should be a tab-separated file in Word2Vec format where the first column contains the word and the remaining columns the values. File can be provided in .txt format or as a zipped text file in .zip or .tar.gz format.
--prune-vectors, -V	flag	Number of vectors to prune the vocabulary to. Defaults to -1 for no pruning.
CREATES	model	A spaCy model containing the vocab and vectors.

Evaluate

Evaluate a model's accuracy and speed on JSON-formatted annotated data. Will print the results and optionally export displaCy visualizations of a sample set of parses to .html files. Visualizations for the dependency parse and NER will be exported as separate files if the respective component is present in the model's pipeline.

$ python -m spacy evaluate [model] [data_path] [--displacy-path] [--displacy-limit]
[--gpu-id] [--gold-preproc]

Argument	Type	Description
model	positional	Model to evaluate. Can be a package or shortcut link name, or a path to a model data directory.
data_path	positional	Location of JSON-formatted evaluation data.
--displacy-path, -dp	option	Directory to output rendered parses as HTML. If not set, no visualizations will be generated.
--displacy-limit, -dl	option	Number of parses to generate per file. Defaults to 25. Keep in mind that a significantly higher number might cause the .html files to render slowly.
--gpu-id, -g	option	GPU to use, if any. Defaults to -1 for CPU.
--gold-preproc, -G	flag	Use gold preprocessing.
CREATES	stdout, HTML	Training results and optional displaCy visualizations.

Package

Generate a model Python package from an existing model data directory. All data files are copied over. If the path to a meta.json is supplied, or a meta.json is found in the input directory, this file is used. Otherwise, the data can be entered directly from the command line. After packaging, you can run python setup.py sdist from the newly created directory to turn your model into an installable archive file.

$ python -m spacy package [input_dir] [output_dir] [--meta-path] [--create-meta] [--force]

### Example
python -m spacy package /input /output
cd /output/en_model-0.0.0
python setup.py sdist
pip install dist/en_model-0.0.0.tar.gz

Argument	Type	Description
input_dir	positional	Path to directory containing model data.
output_dir	positional	Directory to create package folder in.
--meta-path, -m 2	option	Path to meta.json file (optional).
--create-meta, -c 2	flag	Create a meta.json file on the command line, even if one already exists in the directory. If an existing file is found, its entries will be shown as the defaults in the command line prompt.
--help, -h	flag	Show help message and available arguments.
CREATES	directory	A Python package containing the spaCy model.