Rouge Python Packages

rouge-metric

A Python wrapper of the official ROUGE-1.5.5.pl script and a re-implementation of full ROUGE metrics.

rouge-chinese

Python ROUGE Score Implementation for Chinese Language Task (official rouge score)

pyrouge

A Python wrapper for the ROUGE summarization evaluation package

rouge-rust

Rust-backed ROUGE-1, ROUGE-2, and ROUGE-L scoring for Python, with reference-parity tests and parallel batch APIs.

sumeval

Well tested & Multi-language evaluation framework for text summarization.

ranx-k

Korean-optimized RAG evaluation toolkit with Kiwi tokenizer, ROUGE metrics, and IR evaluation for retrieval systems (Hit@K, NDCG@K, MRR, etc.)

fitzyracing-rouge

360 Bench: tested fix for rouge (whitespace-only sentence segments counted as a shared empty word) — published as fitzyracing-rouge on PyPI

xlmtec

xlmtec is a powerful, modular, and interactive command-line tool for fine-tuning Large Language Models (LLMs). Multiple Techniques: Support for LoRA, QLoRA, and Prompt Tuning. Benchmarking: Built-in evaluation with ROUGE and other metrics.

textmetrics

Automatic text metrics (BLEU, ROUGE, METEOR, +++)