wenyi 将被语言阻隔的作品，带到读者的语言中。Bringing literature in @codeKK pythonOpen Source Website

wenyi

Project Url: BigDawnGhost/wenyi

Introduction: 将被语言阻隔的作品，带到读者的语言中。Bringing literature into your language.

More: Author ReportBugs

Tags:

Carry stories across languages.

Translation for books and long-form writing, with the whole work in view.

Whole-book understanding · Consistent terminology · Evidence-based review

Quick start · Language support · Documentation

English | 简体中文

Why Wenyi

Typical approach	Wenyi
Segments translated in isolation, unaware of surrounding content	Whole-book prescan with chapter digests and rolling context
Glossary managed manually or as an afterthought	Real-time term extraction with conflict detection, fed back into subsequent batches
Single-pass translation, fragile to interruptions	Batch checkpoints and chapter status tracking: resume any interrupted run with the same command
Raw model output, no systematic quality process	Translate → polish → evidence-driven whole-book review

Wenyi is designed for long-form texts — novels, social-science monographs, narrative nonfiction, and more.

Wenyi bilingual EPUB preview
_{A bilingual reading sample: translation alongside visually subdued source text.}

Core features

Web workspace — English and Chinese interfaces, live translation progress, paragraph proofreading with revision history, and whole-book review with evidence and publication results.
Whole-book understanding — prescans the source before translation, creating per-chapter digests and a book-level synopsis injected into every batch
Real-time glossary — extracts proper names, terms, and recurring expressions as translation progresses; detects conflicting translations and surfaces them for resolution
Multi-stage quality — optional polishing (strong model) and an evidence-driven whole-book AI review
Resumability — batch-level checkpoints, chapter status tracking, and atomic state writes; interrupt at any point and resume with the same command
Multiple LLM providers — DeepSeek, OpenAI, OpenRouter, OrcaRouter, Google Gemini, Ollama, vLLM, and generic OpenAI-compatible endpoints; keep three convenient tiers or select models per operation, mix connections, and share request limits. See model routing.
Native EPUB preservation — writes translated text back into the original XHTML templates and attempts to preserve styles, images, TOC, and anchors
Bilingual output — optional source-and-translation edition with visually subdued source text, including dark mode support

Interface preview

Track translation progress, usage, and elapsed time, then proofread paragraphs alongside the source. See the deployment guide. Screenshots show the Chinese interface; English is available in Settings.

_{Translation overview: usage by step, cache hit rates, and run durations.}

_{Manual proofreading: compare source and translation; right-click to edit, inspect revisions, or copy text.}

Quick start

Prerequisites

Wenyi requires Python 3.10+ and uv.

Installation

git clone https://github.com/BigDawnGhost/wenyi.git
cd wenyi
uv sync

Configuration

Set your API key:

export DEEPSEEK_API_KEY=sk-...

One-command translation

uv run wenyi translate book.epub

This parses the book, detects the source language, prescans for understanding, translates all chapters, and assembles the output. The monolingual Chinese EPUB is written to output/book.zh.epub by default.

Multilingual translation (experimental): select a direction using language.source / language.target, such as zh → en or en → ja. Run uv run wenyi languages for the list. Targets have separate state and output names. See the usage guide.

Step-by-step workflow

# 1. Prepare — parse, analyze, prescan (no body text translated)
uv run wenyi prepare book.epub

# 2. Translate — resume from the prepared state
uv run wenyi translate book.epub

# 3. Review — independent final review against the completed glossary
uv run wenyi review book.epub

# 4. Check progress
uv run wenyi status book.epub

Interrupt and resume

Every completed batch is persisted immediately. If a run is interrupted, execute the same command again:

uv run wenyi translate book.epub

Command-line overrides

uv run wenyi translate book.epub --polish --review          # enable polishing and final review
uv run wenyi translate book.epub --no-polish                # disable polishing
uv run wenyi translate book.epub --no-review                # skip final review
uv run wenyi translate book.epub --bilingual                # produce both editions
uv run wenyi translate book.epub --chapter 0                # translate the first chapter (indices start at 0)
uv run wenyi translate book.epub --format txt               # export as plain text

Final review runs by default after the complete book has been translated and the glossary has reached its final state. Pass --no-review or set pipeline.review: false to skip it. You can also run Agent Review independently:

uv run wenyi review book.epub
uv run wenyi review book.epub --autofix

Translation batches and fresh Reviewer requests receive the full glossary. Review reuses completed results or resumes unfinished work when content, configuration, and full-glossary fingerprints match; otherwise it starts a new run. It checks chunks concurrently and can selectively request cross-book evidence before resolving contradictory consistency suggestions. See glossary and resume policy.

Confirmed issues can produce provisional full-segment replacements in a run-local shadow translation. A fresh whole-book review sees the shadow text—but not the previous issue explanation—and validates it again. Review publishes to formal chapter target values by default. Pass --no-autofix or set pipeline.review_autofix: false to keep the run read-only. With Autofix, folded changes are applied first and remaining issues reuse the existing Review Agent Loop and Fixer against that updated text. Only formal segment target values are replaced; full history stays in the Review directory's autofix/index.json. The consolidated result, run usage, events, and internal records are written under state/<book>/targets/<target-language>/reviews/review-<timestamp>/.

Supported formats

Input	Output
EPUB, FB2, TXT, Markdown, HTML, PDF, DOCX	EPUB (monolingual / bilingual), TXT, HTML, Markdown, DOCX
SRT (movie / series subtitles)	`.zh.srt` (monolingual) and optional `.zh-bi.srt` (bilingual)

PDF input defaults to MinerU and requires MINERU_API_KEY for the initial conversion; the resulting HTML is cached and reused. The BabelDOC bridge is optional for layout-preserving PDFs.
EPUB output attempts to preserve the original book's styles, images, table of contents, and anchors. Vertical layout is converted to horizontal for Chinese reading.
Source language is auto-detected by default, or fixed to an ISO 639-1 code in config.yaml.
.srt input is auto-detected by translate. It uses a light concurrent path (no glossary, polish, or whole-book review). State lives under state/srt/<slug>/targets/<target-language>/; outputs default to the source file's output/ directory. Details: Usage guide.
.docx input uses the full book pipeline. Headings, simple tables, lists, and common run/paragraph styles are preserved where possible; translated Chinese uses Song (宋体). Default export is .zh.docx (override with --format). Details: Usage guide.

Translation pipeline

Wenyi combines whole-book understanding, batch translation, optional polishing, review, and export. See the translation pipeline for the flowchart and stage details.

Documentation

Usage guide — installation, Windows setup, input/output, resumability, independent stages
Configuration — providers, languages, pipeline switches, segmentation, paths
Translation pipeline — whole-book analysis, terminology, context, polishing, review
Web deployment — Docker/local Web stack, workers, exports, and project workflows
Contributing — development, testing, and contribution guidelines

Translated state directories for public-domain books may be shared through wenyi-bookcase. Do not publish copyrighted text, private books, or state/ directories containing sensitive information without permission.

Limitations

Multilingual translation is experimental: Chinese, English, Japanese, Korean, French, German, Spanish, Italian, Portuguese, Russian, Vietnamese, and selected variants have built-in profiles. Real-model long-form quality still needs evaluation; the CLI and prompt instructions use English, while generated descriptive metadata follows the translation target.
Polishing and final review are the most expensive stages. Shadow fixing may trigger multiple full-book review passes and additional Fixer calls.
PDF input defaults to MinerU and requires an API key for the initial conversion. The BabelDOC bridge is optional for layout-preserving PDFs.
SRT translation is a light concurrent path: no glossary, polishing, or whole-book review, and slug collision is possible for identically named files in different folders.
Translation quality is bounded by the capabilities of the chosen LLM model.
Very long books may produce large state directories; storage requirements grow with book length.