OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Developer Tools & SDKs

Spacy Udpipe

Spacy Udpipe is a Python library that wraps UDPipe pretrained language models as spaCy Language objects. It processes raw, presegmented or pretokenized text into spaCy Docs with token-level linguistic attributes, including lemmas, part-of-speech tags and dependency information.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Spacy Udpipe — OpenViST project profile in AI Developer Tools & SDKs.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when a Python application needs UDPipe model outputs through spaCy Language and Doc objects, particularly for multilingual text or an existing local UDPipe model.

Who it is for

  • Python developers building text-processing applications with spaCy.
  • Teams seeking pretrained UDPipe models for multilingual annotation in a spaCy workflow.
  • Developers who have a local UDPipe model and want to load it through spaCy.

Documented uses

  • Add tokenization and linguistic annotation to an existing spaCy pipeline.
  • Create annotated Docs for downstream NLP processing.
  • Load a custom UDPipe model from a local file.
Before you choose

Requirements & limits

  • The README describes pretrained model coverage for more than 50 languages and links to a list of supported models.
  • Input may be raw text, presegmented text or pretokenized text.
  • The library sets token attributes in its custom Tokenizer, leaving the spaCy Language.pipeline empty.
  • Language-specific tag maps may be needed for XPOS-to-UD POS mappings and morphological features; noun-chunk extraction requires a language-specific syntax iterator.
  • The library source is MIT-licensed, while the README lists pretrained models under CC BY-NC-SA 4.0.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Process text with a pretrained language model

Install Spacy Udpipe, obtain a pretrained model, and create a spaCy Doc containing token annotations.

Before you start

  • Python environment with pip
  • A language code for a supported pretrained UDPipe model

Steps

  1. Install the package with the command below.

    Documented command
    pip install spacy-udpipe

  2. In Python, import spacy_udpipe and download the selected model with spacy_udpipe.download("en"), replacing en with the desired language code.

  3. Load the model with spacy_udpipe.load("en") and pass text to the returned Language object.

  4. Read token attributes such as lemma_, pos_ and dep_ from the resulting Doc.

Expected outcome

A spaCy Doc whose tokens expose the documented linguistic attributes.

Guide limitations

  • Available pretrained models vary by supported language; consult the project’s languages list.
  • The README describes UDPipe models as faster but slightly less accurate than Stanza models.
  • Language-specific tag maps and syntax iterators may be needed for mappings, morphology or noun-chunk extraction.
Documentation 1 ↗
Source-based practical guide

Load a local UDPipe model into spaCy

Create a spaCy Language object using a custom UDPipe model file.

Before you start

  • Python environment with Spacy Udpipe installed
  • A local UDPipe model file and its language code

Steps

  1. Import spacy_udpipe.

  2. Call spacy_udpipe.load_from_path with the language code, model-file path and metadata.

  3. Pass text to the returned Language object and read token attributes from the resulting Doc.

Expected outcome

A spaCy Doc processed with the supplied local UDPipe model.

Guide limitations

  • The README demonstrates the method with a Croatian model and says it can be used for languages supported by spaCy.
  • Language-specific spaCy defaults, tag maps and syntax iterators can affect available mappings and parsing utilities.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
TakeLab/spacy-udpipe · Official homepage title · retained in its source language
How we review sourcesSuggest a correction