gcld3
CLD3 is a neural network model for language identification.
What it is and what it does
gcld3 is a Python wrapper around Google's Compact Language Detector v3, a neural network model trained to identify the language of text. It extracts character n-grams from input, hashes them to embedding vectors, and passes the averaged embeddings through a small neural network to predict language. The model outputs BCP-47 language codes and can distinguish between different scripts of the same language.
The package ships with precompiled inference code and a trained model, so no training or model download is required at runtime. It has no runtime dependencies. However, the package is abandoned—the repository was archived and the last release was 2020-08-19, meaning no bug fixes, security updates, or support for newer Python versions are expected.
Use it for:
- Automatically categorize user-generated content by language for multilingual applications or content moderation pipelines.
- Detect the language of incoming text in chatbots or support systems to route to appropriate handlers.
- Identify the script used in text for rendering or font selection in international user interfaces.
- Preprocess text corpora by filtering or grouping documents by detected language before NLP analysis.
- Validate or correct language metadata in multilingual datasets or document stores.
Worth the install?
AI-flagged interpretation of the facts on this page — verify before relying
Identifies the language of input text using a neural network model, returning BCP-47-style language codes for many languages and scripts.
Yes, if you need lightweight language detection for a stable, well-defined use case and can accept that the package will not receive updates. The model is frozen and the package has no runtime dependencies, so it will continue to work predictably. No, if you require support for modern Python versions, active maintenance, or security patches—use an actively maintained alternative instead.
Install
gcld3 on PyPI
pip
pip install gcld3uv
uv add gcld3poetry
poetry add gcld3Installing gcld3
Before you install
Medium install friction due to compiled wheels for specific Python versions and platforms (macOS, manylinux2010). Package is abandoned as of 2023-05-24 with no active maintenance.
License in practice
License status is unclear—no SPDX identifier or raw license text provided. Verify licensing terms before use in proprietary or redistributed projects.
Quickstart
pip install gcld3
import gcld3
detector = gcld3.NNetLanguageIdentifier(min_num_bytes=0, max_num_bytes=0)
result = detector.FindLanguage(text="Hello world")
print(result.language, result.probability)
Requires prebuilt wheels for specific Python versions on macOS or manylinux2010; building from source requires Chromium repository and build tools.
Verify before relying
- Whether the package works with Python versions beyond those with prebuilt wheels
- Current stability and accuracy of the trained model given no updates since 2020-08-19
- Whether the archived repository will accept security patches or bug fixes
Package facts
| License | not declared (unclear) |
| Python support | not specified |
| Install friction | medium — platform-specific wheel |
| Runtime dependencies | none |
| Maintenance | abandoned — 2,186 days since the last release |
| Last repo commit | (repository archived) |
| First released | |
| Downloads | 109,802/month — #12,498 on PyPI (30-day window, as of 2026-08-14) |
| Known vulnerabilities | none known (OSV.dev, checked 2026-08-14) |
Evidence: gcld3-3.0.13-cp36-cp36m-macosx_10_9_x86_64.whl; gcld3-3.0.13-cp36-cp36m-manylinux2010_x86_64.whl; gcld3-3.0.13-cp38-cp38-macosx_10_9_x86_64.whl; gcld3-3.0.13-cp38-cp38-manylinux2010_x86_64.whl; gcld3-3.0.13-pp36-pypy36_pp73-macosx_10_9_x86_64.whl; gcld3-3.0.13-pp36-pypy36_pp73-manylinux2010_x86_64.whl
Tags
More Linguistic packages
Detects and normalizes text encoding from…
permissive · top 100 on PyPI
tiktokentiktoken is a fast BPE tokenizer that converts…
permissive · top 1,000 on PyPI
chardetDetects character encoding and language in byte…
permissive · top 1,000 on PyPI
text-unidecodeConverts Unicode text to ASCII by…
copyleft · top 1,000 on PyPI
larkLark is a parsing library that builds abstract…
permissive · top 1,000 on PyPI
tree-sitterPython bindings to the tree-sitter parsing…
permissive · top 1,000 on PyPI
lingua-language-detectorDetects which language a text is written in,…
permissive · top 5,000 on PyPI
py3langidIdentifies the language of text in one of 97…
permissive · top 15,000 on PyPI
pycld2Detects the language of text using Google's…
permissive · top 15,000 on PyPI
fasttext-langdetectIdentifies the language of UTF-8 text using…
permissive · top 15,000 on PyPI
langdetectDetects the language of text input, supporting…
permissive · top 5,000 on PyPI
language-dataProvides multilingual language names, speaker…
permissive · top 5,000 on PyPI
minisbdDetects sentence boundaries in text across many…
agpl · top 15,000 on PyPI
bpembBPEmb provides pre-trained subword embeddings…
permissive · top 15,000 on PyPI
clabeValidates and generates CLABE numbers, Mexico's…
permissive · top 15,000 on PyPI
django-zxcvbn-password-validatorA Django password validator that uses pattern…
permissive · top 15,000 on PyPI