rouge-metric
A fast python implementation of full ROUGE metrics for automatic summarization.
Decision gist · record as of 2026-08-14
Yes, if you need ROUGE metrics for summarization evaluation and can tolerate an abandoned package. The library is stable, has low install friction, and produces correct results for its intended use. Install it for research or production summarization evaluation, but do not expect bug fixes or updates. Consider forking or switching to an actively maintained alternative if you encounter issues or need new features.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- The Perl script wrapper requires Perl to be installed; the pure Python implementation has no external dependencies beyond typing.
- Low install friction with only the standard library's typing module as a runtime dependency.
- However, the package is abandoned—last commit was 2021-02-26 and no releases since 2020-10-21—so expect no maintenance or bug fixes going forward.
License · maintenance · safety
MIT (permissive) — MIT license is permissive and imposes no restrictions on use, modification, or distribution in your own projects.
last release 2020-10-21 (2123 days) · last repo commit 2021-02-26 · 21 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 137,312 downloads/mo, #11,371 on PyPI
Alternatives
Verify before relying
pip install rouge-metric
from rouge_metric import PyRouge
rouge = PyRouge(rouge_n=(1, 2), rouge_l=True)
hypotheses = ['how are you i am fine']
references = [['how do you do fine thanks']]
scores = rouge.evaluate(hypotheses, references)
print(scores)- Whether the package's multi-document results differ materially from ROUGE-1.5.5.pl due to the absence of bootstrap resampling in practice.
- Current compatibility with Python versions released after 2020, given the abandoned maintenance status.
What it is and what it does
rouge-metric is a Python library for computing ROUGE (Recall-Oriented Understudy for Gisting Evaluation) metrics, the standard automatic evaluation framework for text summarization. It provides two implementations: a pure Python version that computes ROUGE-N, ROUGE-L, ROUGE-W, ROUGE-S, and ROUGE-SU scores without external process invocation, and a wrapper around the official ROUGE-1.5.5.pl Perl script for compatibility with existing workflows. The Python implementation is language-agnostic and treats documents as token sequences, letting you apply your own tokenization (e.g., nltk for English, jieba for Chinese) before scoring.
The package is designed for researchers and practitioners evaluating automatic summarization systems. It supports single and multiple references per hypothesis, batch evaluation over document collections, and both command-line and programmatic APIs. The pure Python path is fast and produces identical results to the Perl reference on single-document scenarios. However, the project is abandoned as of 2020 and receives no maintenance or updates.
Use it for
- Evaluate generated summaries against reference summaries in a summarization research project or benchmark.
- Batch-score multiple hypothesis-reference pairs from files to compare summarization model outputs.
- Integrate ROUGE scoring into an NLP pipeline for multi-lingual text summarization with custom tokenization.
- Reproduce results from published summarization papers that report ROUGE-1, ROUGE-2, ROUGE-L metrics.
- Compare summarization systems using command-line ROUGE scoring 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 metrics for summarization evaluation and can tolerate an abandoned package.
The library is stable, has low install friction, and produces correct results for its intended use. Install it for research or production summarization evaluation, but do not expect bug fixes or updates. Consider forking or switching to an actively maintained alternative if you encounter issues or need new features.
Install
rouge-metric on PyPI
Before you install
Low install friction with only the standard library's typing module as a runtime dependency. However, the package is abandoned—last commit was 2021-02-26 and no releases since 2020-10-21—so expect no maintenance or bug fixes going forward.
The Perl script wrapper requires Perl to be installed; the pure Python implementation has no external dependencies beyond typing.
License in practice
MIT license is permissive and imposes no restrictions on use, modification, or distribution in your own projects.
Quickstart
pip install rouge-metric
from rouge_metric import PyRouge
rouge = PyRouge(rouge_n=(1, 2), rouge_l=True)
hypotheses = ['how are you i am fine']
references = [['how do you do fine thanks']]
scores = rouge.evaluate(hypotheses, references)
print(scores)Verify before relying
- Whether the package's multi-document results differ materially from ROUGE-1.5.5.pl due to the absence of bootstrap resampling in practice.
- Current compatibility with Python versions released after 2020, given the abandoned maintenance status.
Package facts
| License | MIT permissive |
| Python support | Supports the current Python release >=2.7,!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.* |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 1 packagetyping |
| Maintenance | Abandoned 2,123 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 137,312 / month, #11,371 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 4 - BetaIntended Audience :: Science/ResearchLicense :: OSI Approved :: MIT LicenseProgramming Language :: Python :: 2Programming Language :: Python :: 3Topic :: Text Processing :: Linguistic |
Evidence: rouge_metric-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 › “summarization evaluation”
- rouge-metricComputes ROUGE metrics (ROUGE-N, ROUGE-L, ROUGE-W, ROUGE-S, ROUGE-SU)…
- rougeComputes ROUGE scores (Recall-Oriented Understudy for Gisting…
- 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 · rouge-chinese · rouge-score · pycocoevalcap · texterrors · bert-score · unbabel-comet · ragas · pytextrank · kaldialign