rouge
Full Python ROUGE Score Implementation (not a wrapper)
Decision gist · record as of 2026-08-14
Yes, if you need ROUGE scoring for summarization evaluation and can accept dormant maintenance. The package is lightweight, has no known vulnerabilities, and works reliably for its stated purpose. However, verify that slight differences from official ROUGE-155 are acceptable for your use case, and be aware that no updates are forthcoming—use it as a stable tool, not one under active development.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Low friction: pure Python wheel with a single dependency (six).
- Maintenance is dormant—last release was 2021-07-20 and no commits since 2024-11-19—so expect no active bug fixes or feature updates.
License · maintenance · safety
LICENCE.txt (unclear) — License treatment is unclear: the package references LICENCE.txt but provides no SPDX identifier. Review the repository's license file before adopting in proprietary or license-sensitive contexts.
last release 2021-07-20 (1851 days) · last repo commit 2024-11-19 · 720 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 898,402 downloads/mo, #4,781 on PyPI
Alternatives
Verify before relying
pip install rouge
from rouge import Rouge
rouge = Rouge()
scores = rouge.get_scores(
"generated summary text",
"reference summary text"
)
print(scores)- How closely results match the official ROUGE-155 implementation beyond the acknowledged slight differences mentioned in the repository
- Whether the package is actively maintained or if dormancy poses risks for new Python versions or dependencies
What it is and what it does
Rouge is a pure Python implementation of the ROUGE metric, a standard evaluation framework for text summarization. It computes precision, recall, and F1 scores across ROUGE-1 (unigram), ROUGE-2 (bigram), and ROUGE-L (longest common subsequence) variants to quantify how well a generated summary matches reference text. The package works both as a command-line tool and as a library, accepting single sentences, multiple sentence pairs, or entire files for batch scoring.
The implementation is independent from the official ROUGE-155 script, so results may differ slightly. It depends only on six and installs with low friction. The codebase is dormant (last release July 2021), so it receives no active maintenance, though the repository remains unarchived and the code is stable for existing use cases.
Use it for
- Evaluate abstractive text summarization models by comparing generated summaries to human-written references
- Batch-score multiple hypothesis-reference pairs from files to assess summarization system performance
- Integrate ROUGE scoring into NLP evaluation pipelines for research or production summarization systems
- Command-line scoring of individual text pairs without writing Python code
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you need ROUGE scoring for summarization evaluation and can accept dormant maintenance.
The package is lightweight, has no known vulnerabilities, and works reliably for its stated purpose. However, verify that slight differences from official ROUGE-155 are acceptable for your use case, and be aware that no updates are forthcoming—use it as a stable tool, not one under active development.
Install
rouge on PyPI
Before you install
Low friction: pure Python wheel with a single dependency (six). Maintenance is dormant—last release was 2021-07-20 and no commits since 2024-11-19—so expect no active bug fixes or feature updates.
License in practice
License treatment is unclear: the package references LICENCE.txt but provides no SPDX identifier. Review the repository's license file before adopting in proprietary or license-sensitive contexts.
Quickstart
pip install rouge
from rouge import Rouge
rouge = Rouge()
scores = rouge.get_scores(
"generated summary text",
"reference summary text"
)
print(scores)Verify before relying
- How closely results match the official ROUGE-155 implementation beyond the acknowledged slight differences mentioned in the repository
- Whether the package is actively maintained or if dormancy poses risks for new Python versions or dependencies
Package facts
| License | LICENCE.txt unclear |
| Python support | Not specified |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 1 packagesix |
| Maintenance | Dormant 1,851 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 898,402 / month, #4,781 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Intended Audience :: Science/ResearchProgramming Language :: Python :: 3Topic :: Text Processing :: Linguistic |
Evidence: rouge-1.0.1-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “ROUGE score calculation”
- rougeComputes ROUGE scores (Recall-Oriented Understudy for Gisting…
- rouge-scoreComputes ROUGE scores (ROUGE-N, ROUGE-L, ROUGE-Lsum) to evaluate the…
- rouge-chineseComputes ROUGE evaluation metrics for Chinese text summarization and…
Give your agent the search over MCP, or paste the wish link into any chat.
More Linguistic packages
Detects and normalizes text encoding from unknown or ambiguous sources, supporting all IANA character sets that Python's core library provides codecs for, with the ability to register custom codecs.
tiktoken is a fast BPE tokenizer that converts text into token sequences compatible with OpenAI models, supporting multiple encoding schemes including o200k_base and model-specific encodings.
Install it if you work with OpenAI APIs or need to understand token boundaries in GPT-family models.
Detects character encoding and language in byte sequences with high accuracy, supporting 99 encodings and returning confidence scores, language tags, and MIME types.
Install it if you need to detect character encoding or language in byte data; the rewrite makes it substantially faster and more accurate than its predecessors.
Converts Unicode text to ASCII by transliterating non-ASCII characters into their closest ASCII equivalents, with no runtime dependencies.
However, if transliteration quality or ongoing maintenance matters, consider unidecode instead despite its GPL-only license.
Lark is a parsing library that builds abstract syntax trees from context-free grammars, supporting multiple parsing algorithms (Earley, LALR(1), CYK) with automatic line and column tracking.
Python bindings to the tree-sitter parsing library, enabling incremental parsing and syntax tree analysis for source code.
See also rouge-chinese · rouge-metric · textstat · unbabel-comet · rouge-score · dtlpymetrics · pycocoevalcap · seqeval · texterrors · bert-score