Immersive Translate Site/Immersive Translate Document App — Chinese (Traditional, Hong Kong) @ Weblate: BabelDOC uses parallel processing technology, and processing speed varies depending …

The translation is temporarily closed for contributions due to maintenance, please come back later.
The translation was automatically locked due to following alerts: Could not push the repository.

Zen

Translation

Key babelDoc.answer.performance

English

BabelDOC uses parallel processing technology, and processing speed varies depending on document characteristics: - Documents around 50 pages: usually completed in 1-5 minutes
- Documents around 500 pages: about 10-20 minutes to complete
- Documents around 1000 pages: about 10-20 minutes to complete
- Documents around 5000 pages: about 1-2 hours to complete
- Processing time is affected by document complexity, server load, and other factors. To ensure translation quality, we perform multiple optimization processes on each paragraph, including format analysis, text extraction, and translation optimization.

Chinese (Traditional, Hong Kong)

Needs editing

This translation is currently locked.

Skip

Key	English	Chinese (Traditional, Hong Kong)
babelDoc.useFreeModal	Continue translating using free AI models.	使用免費 AI 模型繼續翻譯
babelDoc.pdf-page-count-error	Unable to retrieve the number of PDF pages, please contact the developer for assistance.	無法獲取 PDF 頁數，請聯繫開發人員處理。
babelDoc.uploadingFile	Uploading file··· {{percent}}%	正在上傳文件··· {{percent}}%
babelDoc.createTask	Creating task... {{percent}}%	正在創建任務··· {{percent}}%
babelDoc.page-count-is-too-large	The document appears to exceed the limit, please paginate and try translating again.	文件似乎超出了限制，請分頁後再嘗試翻譯。
babelDoc.translationMap.Waiting in line	Queuing... {{percent}}%	正在排隊··· {{percent}}%
babelDoc.network-error	It seems there is an issue with the internet. Please check your network connection and try again!	網絡似乎出現了一些問題，請您檢查一下網絡連接後再試一次哦！
tips	Warm reminder	溫馨提示
continueTranslate	Continue translating	繼續翻譯
cancelTranslate	Cancel translation	取消翻譯
babelDoc.max-processing-records	The current queue is quite long, and the system's processing capacity has reached its limit. We are working hard to expand our capacity. Please try again later. Thank you for your understanding and patience!	目前排隊人數較多，系統處理能力已達上限。我們正在努力擴容，請您稍後再嘗試，感謝您的理解與耐心！
babelDoc.max-processing-records-per-user	Batch translation is currently not supported, and each user can only process one file at a time. Please submit a new translation request after the current task is completed.	目前暫不支持批量翻譯，每位用戶在同一時間僅能處理一個文件。請您在當前任務完成後再提交新的翻譯請求。
babelDoc.iOSRenderPdfError	Due to the limitations of iOS and iPadOS, the preview of PDF files on this device may be incomplete. Please try exporting and viewing the file, or view it on a non-iPhone/iPad device for the best experience.	由於 iOS 和 iPadOS 的限制，PDF 文件在此設備上的預覽可能不完整，請嘗試導出後查看，或者在非 iPhone/iPad 的設備中查看以獲得最佳體驗。
babelDoc.cf-turnstile-error	Cloudflare verification code error, please re-upload.	Cloudflare 驗證碼錯誤，請重新上傳。
babelDocQuotaError.notOfficialPro	Your monthly page quota is insufficient and will reset at the beginning of next month. Becoming a full member entitles you to a quota of 10,000 pages. Thank you for your patience and support.	您的本月頁數額度已用完，將於下月初重置，成為正式會員可享受 10000 頁額度。感謝您的耐心與支持。
babelDoc.answer.performance	BabelDOC uses parallel processing technology, and processing speed varies depending on document characteristics:<br/><br/>- Documents around 50 pages: usually completed in 1-5 minutes - Documents around 500 pages: about 10-20 minutes to complete - Documents around 1000 pages: about 10-20 minutes to complete - Documents around 5000 pages: about 1-2 hours to complete - Processing time is affected by document complexity, server load, and other factors.<br/>To ensure translation quality, we perform multiple optimization processes on each paragraph, including format analysis, text extraction, and translation optimization.	BabelDOC 採用並行處理技術，處理速度因文檔特點而異：<br/><br/><ul><li>50 頁左右文檔：通常 1-5 分鐘完成</li><li>500 頁左右文檔：約 10-20 分鐘完成</li><li>1000 頁左右文檔：約 10-20 分鐘完成</li><li>5000 頁左右文檔：約 1-2 小時完成</li><li>處理時間受文檔複雜度、伺服器負載等因素影響</li></ul><br/>為確保翻譯品質，我們對每個段落進行多重優化處理，包括格式分析、文本提取、翻譯優化等步驟。
babelDoc.problem.requireCompatibility	When is it necessary to enable compatibility mode?	何時需要啟用兼容模式？
babelDoc.problem.compatibilityInfluence	What is the impact of enabling compatibility mode?	啟用兼容模式的影響是什麼？
babelDoc.feedbackDrainage	Try our new product <a href="https://app.immersivetranslate.com/babel-doc/" target="_blank" style="text-decoration: underline; color: #ea4c89;">BabelDOC</a> (non-scanned version)	試試我們的新產品 <a href="https://app.immersivetranslate.com/babel-doc/" target="_blank" style="text-decoration: underline; color: #ea4c89;">BabelDOC</a>（非掃描版）
babelDoc.answer.requireCompatibility	When compatibility mode is not enabled and the following issues occur in the translation, you need to enable compatibility mode: <br/><br/><ol><li>Colored blocks turn black and affect reading</li><li>The entire page of text suddenly disappears</li><li>Each character in parts of the document has a space in between</li></ol>	在未啟用兼容模式，且譯文出現以下情況時，您需要啟用兼容模式：<br/><br/><ol><li>彩色色塊變成黑色且影響閱讀</li><li>整頁文字突然消失</li><li>部分論文每個字中間都有一個空格</li></ol>
babelDoc.answer.compatibilityInfluence	After enabling compatibility mode, BabelDOC will disable rich text translation, skip font subsetting, document cleanup, and drawing instruction optimization steps, resulting in increased file size.	啟用兼容模式後，BabelDOC 將禁用富文本翻譯、跳過字體子集化、文件清理和繪製指令優化步驟，從而導致文件體積增大。
babelDoc.fileSizeError	Please upload a PDF file smaller than {{max_size}}.	請上傳小於 {{max_size}} 的 PDF 文件
modal.glm-4-plus	GLM 4.7	智谱 4.7
modal.doubao	Doubao	豆包
modal.glm-4-flash	GLM-4-Flash	智谱 4 Flash
babelDoc.turnstile-error	Human verification failed, please return to the homepage to re-upload.	人機驗證失敗，請返回首頁重新上傳。
translateFile.mobile	File	文件
translateText.mobile	Text	文本
translateImage.mobile	Image	圖片
immediateTranslate.pageNums.insufficient.babeldoc.translation	Based on the number of pages in the document, this translation is estimated to consume {{needToken}} Tokens, while your general translation quota has only {{availableToken}} Tokens remaining. You can switch to the free GLM-4-Flash model, or expand your quota by <a href="https://immersivetranslate.com/topup/?type=open_ai&utm_source=app&utm_medium=app&utm_campaign=babel_doc" target="_blank" style="text-decoration: underline;">purchasing an additional package</a>.	根據文件頁數計算，本次翻譯預計需要消耗 {{needToken}} Token，而您的通用翻譯額度僅剩 {{availableToken}} Token。您可以切換至免費的 GLM-4-Flash 模型，或通過 <a href="https://immersivetranslate.com/topup/?type=open_ai&utm_source=app&utm_medium=app&utm_campaign=babel_doc" target="_blank" style="text-decoration: underline;">購買加量包</a> 來擴展額度。
immediateTranslate.pageNums.insufficient.babeldoc.translation.free	The current model is the Pro model. You can switch to the free GLM-4-Flash model, or <a href="https://immersivetranslate.com/pricing/?utm_source=app&utm_medium=app&utm_campaign=babel_doc" target="_blank" style="text-decoration: underline;">become a Pro member</a> to use the Pro model.	當前模型為 Pro 模型，您可以切換至免費的 GLM-4-Flash 模型，或<a href="https://immersivetranslate.com/pricing/?utm_source=app&utm_medium=app&utm_campaign=babel_doc" target="_blank" style="text-decoration: underline;">成為 Pro 會員</a>來使用 Pro 模型。

Key	English	Chinese (Traditional, Hong Kong)
allSelect	Select All	全選
applyTerminologyNum	{{num}} applied	已應用 {{num}} 個
auto	Detect source language	檢測源語言
autoDetect	Auto Detect	（自動檢測）
babelDoc.answer.advantage	BabelDOC has the following core advantages in the field of PDF translation:<br/><br/><ol><li><b>Accurate typesetting restoration</b>: Unique layout analysis technology that fully retains the typesetting details of the original document, including fonts, colors, spacing, etc.</li><li><b>Intelligent formula processing</b>: Advanced formula recognition technology that ensures perfect mixing of mathematical formulas and text</li><li><b>Professional field optimization</b>: Specially optimized for professional documents such as academic papers to provide more accurate translation effects</li></ol>	BabelDOC 在 PDF 翻譯領域具有以下核心優勢：<br/><br/><ol><li><b>精準排版還原</b>：獨特的版面分析技術，完整保留原文檔的排版細節，包括字體、顏色、間距等</li><li><b>智能公式處理</b>：先進公式識別技術，確保數學公式與文本的完美混排</li><li><b>專業領域優化</b>：針對學術論文等專業文獻進行特殊優化，提供更準確的翻譯效果</li></ol>
babelDoc.answer.application	<ol><li>Academic paper translation: journal papers, conference papers, research reports, etc.</li><li>E-books: books, technical manuals, etc. (with a low proportion of tables)</li><ol>	<ol><li>學術論文翻譯：期刊論文、會議論文、研究報告等</li><li>電子書籍：書籍、技術手冊等（表格佔比較低的）</li><ol>
babelDoc.answer.compatibilityInfluence	After enabling compatibility mode, BabelDOC will disable rich text translation, skip font subsetting, document cleanup, and drawing instruction optimization steps, resulting in increased file size.	啟用兼容模式後，BabelDOC 將禁用富文本翻譯、跳過字體子集化、文件清理和繪製指令優化步驟，從而導致文件體積增大。
babelDoc.answer.concurrent	Single File Translation: When using the "Single File" translation feature, the system only supports one translation task at a time.<br/>Batch Translation (Exclusive for Pro Members): Pro members can enjoy the batch translation feature, which allows up to 100 translation tasks to be queued simultaneously (limited-time test). Although the processing priority of batch translation tasks is lower than that of single file translations, this feature enables you to submit and translate a large number of files at once, enhancing work efficiency.<br/><br/>During peak periods of high system load, we prioritize the processing speed of single file translation tasks for Pro members to ensure a better user experience. The counts of single file translation and batch translation tasks are calculated independently.	單個文件翻譯：所有用戶在使用“單個文件”翻譯功能時，系統僅支持同時進行一個翻譯任務。<br/>批量翻譯（Pro 會員專屬）：Pro 會員可享受批量翻譯功能，最多可同時排隊 100 個翻譯任務（限期測試）。雖然批量翻譯任務的處理優先級低於單個文件翻譯，但此功能允許您一次性提交並翻譯大量文件，提高工作效率。<br/><br/>在系統負載較高的高峰時段，我們會優先保證 Pro 會員的單文件翻譯任務處理速度，確保會員獲得更佳的使用體驗。單個文件翻譯和批量翻譯的任務數獨立計算。
babelDoc.answer.customApi	<ol><li>Security Risk: BabelDOC uses a backend translation architecture, and if custom APIs are allowed, users must submit their API Key to the backend. This not only involves key security issues but also risks malicious attacks (such as DDoS) due to the exposure of backend server IPs, severely affecting service stability.</li><li>Network Uncertainty: The backend needs to actively access the API provided by the user, which may cause the overall translation process to be abnormal due to network delays, cross-regional access failures, or unstable intermediate links.</li><li>Uncontrollable Performance: BabelDOC's backend may issue hundreds of concurrent requests per second. We cannot predict the processing capacity of user APIs, and if the concurrency capacity is low, it will directly affect the overall translation speed and stability.</li><li>Disproportionate Resource Costs: If delays occur due to insufficient performance of user-customized APIs, the system will need to allocate additional computing resources for compensation. This will lead to resource wastage, and there is currently no reasonable way to account for costs and share charges.</li><li>High Architectural Complexity: If custom APIs are called via frontend relay, it will introduce more network hops and reliability challenges, and have a significant negative impact on performance, stability, and user experience.</li></ol><br/>In conclusion, BabelDOC will not support the integration of custom APIs at this stage. Our current focus is on continuously improving the translation quality and stability of BabelDOC. In the future, as the system matures, we will further explore and evaluate more flexible business models and possibilities for functional expansion.	<ol><li>安全性風險：BabelDOC 採用後端翻譯架構，若允許自定義 API，用戶需將 API Key 提交至後端。這不僅涉及密鑰安全問題，還存在因暴露後端伺服器 IP 而可能被惡意攻擊（如 DDoS）的風險，嚴重影響服務穩定性。</li><li>網絡不確定性：後端需主動訪問用戶提供的 API，可能因網絡延遲、跨地域訪問失敗或中間鏈路不穩定，導致整體翻譯流程異常。</li><li>性能不可控：BabelDOC 後端每秒可能發出上百個並發請求。我們無法預測用戶 API 的處理能力，一旦並發能力較低，將直接影響整體翻譯速度與穩定性。</li><li>資源成本不對等：若因用戶自定義 API 性能不足導致任務延遲，系統需額外分配算力資源進行補償。這將造成資源浪費，而現階段並無合理方式進行成本核算與收費分攤。</li><li>架構複雜度高：如通過前端中轉調用自定義 API，則會引入更多網絡跳數和可靠性挑戰，並對性能、穩定性及用戶體驗造成重大負面影響。</li></ol><br/>綜上，BabelDOC 在現階段不會支持自定義 API 的接入。我們當前的重點是持續提升 BabelDOC 的翻譯質量與穩定性。未來在系統更加成熟之後，我們會進一步探索和評估更靈活的商業模式與功能拓展可能。
babelDoc.answer.difference	The main differences between BabelDOC and immersive translation in PDF processing are:<br/><br/><ol><li><b>Typesetting retention:</b> BabelDOC focuses on fully retaining the typesetting of the original document, including details such as fonts, colors, and spacing, rather than reformatting.</li><li><b>Formula mixed typesetting support:</b> BabelDOC can intelligently process mixed typesetting of mathematical formulas, ensuring the mixing effect of formulas and text.</li><li><b>Professional field support:</b> Specially optimized for the translation effects of professional documents such as academic papers.</li></ol>	BabelDOC 與沉浸式翻譯在 PDF 處理方面有以下主要區別：<br/><br/><ol><li><b>排版保留：</b>BabelDOC 專注於完整保留原文檔的排版，包括字體、顏色、間距等細節，而不是重排。</li><li><b>公式混排支持：</b>BabelDOC 能夠智能處理數學公式混排，確保公式與文本的混排效果。</li><li><b>專業領域支持：</b>特別優化了學術論文等專業文獻的翻譯效果。</li></ol>
babelDoc.answer.knownLimitations	The current version has the following limitations, which we are actively optimizing: <ol> <li>Some formula sections may overlap.</li> <li>Italicized text in translations will disappear.</li> <li>Small sections (such as author information, citations, table of contents entries, etc.) may not be accurately recognized.</li> <li>Only supports languages written in Latin, Chinese, Japanese, or Korean scripts as the source language.</li> <li>Does not support underlining.</li> <li>Does not support translation of chart areas.</li> <li>Does not support drop caps.</li> <li>Does not support PDF Outline translation.</li> <li>Does not support scanned, image-based, or OCR-based PDFs.</li> <li>Does not support ligatures.</li> <li>Does not support blueprints.</li> <li>Does not support Type3 fonts.</li> <li>Does not support image format inline formulas.</li> <li>Does not support right-to-left formatted documents.</li> <li>Only supports horizontally aligned text.</li> </ol>	當前版本存在以下限制，我們正在積極優化：<ol><li>部分公式段落可能出現重疊</li><li>譯文中傾斜的文本會消失</li><li>小型段落（如作者信息、引文、目錄條目等）可能識別不準</li><li>僅支持使用拉丁字母或中日韓文書寫的語言作為原語言</li><li>不支持下劃線</li><li>不支持圖表區域翻譯</li><li>不支持首字下沉效果</li><li>不支持 PDF Outline 翻譯</li><li>不支持掃描版、圖片版及 OCR 版 PDF</li><li>不支持連字</li><li>不支持圖紙</li><li>不支持使用 Type3 字體</li><li>不支持圖片格式的行內公式</li><li>不支持從右到左排版的文件</li><li>僅支持水平橫排文本</li></ol>
babelDoc.answer.noApplication	<ol><li>Scanned PDFs: including OCR processed documents</li><li>Academic submissions: not recommended for direct use in paper submissions</li></ol>	<ol><li>掃描版 PDF：包括 OCR 處理過的文件</li><li>學術投稿：不建議直接用於論文投稿</li><li>報紙</li><li>雜誌</li></ol>
babelDoc.answer.notGood	BabelDOC is still in the early development stage, and the translation effect may not be as expected. We are working hard to improve. If you encounter a problem, please use the feedback button on the top right of the translation result page to report it, and we will improve it as soon as possible.	當前 BabelDOC 仍處於早期開發階段，翻譯效果可能不如預期，我們正在努力改進中。如果您碰到問題，請通過翻譯結果頁面右上角的問題反饋按鈕反饋，我們將在第一時間改進。
babelDoc.answer.overlapping	This is because the original file is a scanned PDF after OCR processing. You can try enabling the OCR temporary solution and retry (only supports white background with black text PDFs).	這是因為原始文件是 OCR 後的掃描版 PDF，您可以嘗試啟用 OCR 版臨時解決方案重新嘗試（僅支持白底黑字 PDF）
babelDoc.answer.performance	BabelDOC uses parallel processing technology, and processing speed varies depending on document characteristics:<br/><br/>- Documents around 50 pages: usually completed in 1-5 minutes - Documents around 500 pages: about 10-20 minutes to complete - Documents around 1000 pages: about 10-20 minutes to complete - Documents around 5000 pages: about 1-2 hours to complete - Processing time is affected by document complexity, server load, and other factors.<br/>To ensure translation quality, we perform multiple optimization processes on each paragraph, including format analysis, text extraction, and translation optimization.	BabelDOC 採用並行處理技術，處理速度因文檔特點而異：<br/><br/><ul><li>50 頁左右文檔：通常 1-5 分鐘完成</li><li>500 頁左右文檔：約 10-20 分鐘完成</li><li>1000 頁左右文檔：約 10-20 分鐘完成</li><li>5000 頁左右文檔：約 1-2 小時完成</li><li>處理時間受文檔複雜度、伺服器負載等因素影響</li></ul><br/>為確保翻譯品質，我們對每個段落進行多重優化處理，包括格式分析、文本提取、翻譯優化等步驟。
babelDoc.answer.quota	We currently use a "translation quota" based billing method, detailed as follows:<br/><br/><ul><li>Translation quotas are charged based on the number of <b>Tokens</b> used during the translation process.</li><li>The <b>GLM-4-Flash-250414</b> model is available to all users, and every BabelDOC user receives a monthly quota of 500,000 Tokens for free model translations within BabelDOC. (Actual availability depends on the supply from upstream suppliers, and quotas are dynamically adjusted based on server load)</li><li>Models such as <b>Qwen-Plus/DeepSeek-V3.2/Doubao-1.5-pro/GPT-5-mini/Gemini-2.5-Flash/Kimi+Qwen/Kimi+DeepSeek/GLM-4.7</b> are exclusively for <b>Pro/Max</b> members, counted towards the members' general translation quota. Pro members enjoy up to <b>20 million Tokens</b> per month, while Max members can enjoy up to <b>50 million Tokens</b> per month. Failed translations are not counted towards the translation quota.</li></ul><br/>At the start of a translation task, the system will deduct the general translation quota in advance based on the calculation of "3000 Tokens × number of pages". Once the translation is complete, we will settle based on actual consumption, refunding any excess to your account, or requiring additional if insufficient. If any system errors occur during the translation, all deducted general translation quotas will be fully refunded to your account. When the automatic term extraction feature is not enabled, the deduction per page is 3000 Tokens/page. When the automatic term extraction feature is enabled, the deduction per page is 6000 Tokens/page.<br/><br/>From actual usage statistics, when automatic term extraction is enabled, the average consumption is about 7381.56 Tokens per page, with the P25–P75 range being 4215.42–9490.89 Tokens; when automatic term extraction is disabled, the average consumption is about 4702.98 Tokens per page, with the P25–P75 range being 2642.38–5797.40 Tokens. Here, P25 (the 25th percentile) indicates that 25% of the pages consume fewer Tokens than this value, and P75 (the 75th percentile) indicates that 75% of the pages consume fewer Tokens than this value. The P25–P75 range is used to describe the common consumption range for most pages, thereby reducing the impact of extreme samples on the overall assessment.	我們目前採用基於「翻譯額度」的計費方式，具體說明如下： <ul><li>翻譯額度按照翻譯過程中使用的 <b> Token 數量 </b> 進行計費。</li><li><b> GLM-4-Flash-250414 </b> 模型所有用戶可用，所有 BabelDOC 用戶每月可獲得 50 萬 Token 額度，用來在 BabelDOC 中使用免費模型翻譯文件。（實際可用性取決於上游供應商的供應情況，額度根據伺服器負載動態調整）</li><li><b> Qwen-Plus/DeepSeek-V3.2/Doubao-1.5-pro/GPT-5-mini/Gemini-2.5-Flash/Kimi+Qwen/Kimi+DeepSeek/GLM-4.7 </b> 模型僅限 <b> Pro/Max </b> 會員使用，計入會員通用翻譯額度，Pro 會員每月可享受 <b> 高達 2000 萬 Token </b> 的翻譯額度，Max 會員每月可享受 <b> 高達 5000 萬 Token </b> 的翻譯額度。失敗的翻譯不計入翻譯額度。</li></ul> 在翻譯任務啟動時，系統將根據"3000 Token × 翻譯頁數"的計算方式預先扣除相應的通用翻譯額度。待翻譯完成後，我們將按實際消耗進行結算，多餘額度將退還至您的賬戶，不足部分則需補充。若翻譯過程中遇到任何系統錯誤，所有預扣的通用翻譯額度將自動全額返還至您的賬戶。當不啟用自動提取術語時，單頁預扣 Token 數為 3000 Token/頁。當啟用自動提取術語功能時，單頁預扣 Token 數為 6000 Token/頁。<br/><br/>從實際使用統計來看，啟用自動術語提取時，平均每頁約消耗 7381.56 Token，其中 P25–P75 區間為 4215.42–9490.89 Token；關閉自動術語提取時，平均每頁約消耗 4702.98 Token，P25–P75 區間為 2642.38–5797.40 Token。其中，P25（第 25 百分位）表示有 25% 的頁面 Token 消耗低於該值，P75（第 75 百分位）表示有 75% 的頁面 Token 消耗低於該值，P25–P75 區間可用於描述大多數頁面的常見消耗範圍，從而減少極端樣本對整體評估的干擾。
babelDoc.answer.quota.cn	We currently use a "translation quota" based billing method, detailed as follows:<br/><br/><ul><li>Translation quotas are charged based on the number of <b>Tokens</b> used during the translation process.</li><li>The <b>GLM-4-Flash-250414</b> model is available to all users, and every BabelDOC user receives a monthly quota of 500,000 Tokens for free model translations within BabelDOC. (Actual availability depends on the supply from upstream providers, and quotas are dynamically adjusted based on server load)</li><li>The <b>Qwen-Plus/DeepSeek-V3.2/Doubao-1.5-pro/Kimi+Qwen/Kimi+DeepSeek/GLM-4.7</b> models are exclusively for <b>Pro/Max</b> members, counted towards the members' general translation quota. Pro members enjoy up to <b>20 million Tokens</b> per month, while Max members enjoy up to <b>50 million Tokens</b> per month. Failed translations are not counted towards the quota.</li></ul><br/>At the start of a translation task, the system will deduct the general translation quota in advance based on "3000 Tokens × number of pages". Once the translation is complete, we will settle based on actual consumption, refunding any excess to your account or requesting additional tokens if there is a shortfall. If any system errors occur during the translation, all pre-deducted general translation quotas will be fully refunded to your account. When the automatic term extraction feature is not enabled, the pre-deduction per page is 3000 Tokens/page. When the automatic term extraction feature is enabled, the pre-deduction per page is 6000 Tokens/page.<br/><br/>From actual usage statistics, when automatic term extraction is enabled, the average consumption is about 7381.56 Tokens per page, with the P25–P75 range being 4215.42–9490.89 Tokens; when automatic term extraction is disabled, the average consumption is about 4702.98 Tokens per page, with the P25–P75 range being 2642.38–5797.40 Tokens. Here, P25 (the 25th percentile) indicates that 25% of the pages consume fewer Tokens than this value, and P75 (the 75th percentile) indicates that 75% of the pages consume fewer Tokens than this value. The P25–P75 range is used to describe the common consumption range for most pages, thereby reducing the impact of extreme samples on the overall assessment.	我們目前採用基於「翻譯額度」的計費方式，具體說明如下： <ul><li>翻譯額度按照翻譯過程中使用的 <b> Token 數量 </b> 進行計費。</li><li><b> GLM-4-Flash-250414 </b> 模型所有用戶可用，所有 BabelDOC 用戶每月可獲得 50 萬 Token 額度，用來在 BabelDOC 中使用免費模型翻譯文件。（實際可用性取決於上游供應商的供應情況，額度根據伺服器負載動態調整）</li><li><b> Qwen-Plus/DeepSeek-V3.2/Doubao-1.5-pro/Kimi+Qwen/Kimi+DeepSeek/GLM-4.7 </b> 模型僅限 <b> Pro/Max </b> 會員使用，計入會員通用翻譯額度，Pro 會員每月可享受 <b> 高達 2000 萬 Token </b> 的翻譯額度，Max 會員每月可享受 <b> 高達 5000 萬 Token </b> 的翻譯額度。失敗的翻譯不計入翻譯額度。</li></ul> 在翻譯任務啟動時，系統將根據"3000 Token × 翻譯頁數"的計算方式預先扣除相應的通用翻譯額度。待翻譯完成後，我們將按實際消耗進行結算，多餘額度將退還至您的賬戶，不足部分則需補充。若翻譯過程中遇到任何系統錯誤，所有預扣的通用翻譯額度將自動全額返還至您的賬戶。當不啟用自動提取術語時，單頁預扣 Token 數為 3000 Token/頁。當啟用自動提取術語功能時，單頁預扣 Token 數為 6000 Token/頁。<br/><br/>從實際使用統計來看，啟用自動術語提取時，平均每頁約消耗 7381.56 Token，其中 P25–P75 區間為 4215.42–9490.89 Token；關閉自動術語提取時，平均每頁約消耗 4702.98 Token，P25–P75 區間為 2642.38–5797.40 Token。其中，P25（第 25 百分位）表示有 25% 的頁面 Token 消耗低於該值，P75（第 75 百分位）表示有 75% 的頁面 Token 消耗低於該值，P25–P75 區間可用於描述大多數頁面的常見消耗範圍，從而減少極端樣本對整體評估的干擾。
babelDoc.answer.requireCompatibility	When compatibility mode is not enabled and the following issues occur in the translation, you need to enable compatibility mode: <br/><br/><ol><li>Colored blocks turn black and affect reading</li><li>The entire page of text suddenly disappears</li><li>Each character in parts of the document has a space in between</li></ol>	在未啟用兼容模式，且譯文出現以下情況時，您需要啟用兼容模式：<br/><br/><ol><li>彩色色塊變成黑色且影響閱讀</li><li>整頁文字突然消失</li><li>部分論文每個字中間都有一個空格</li></ol>
babelDoc.answer.requireOCR	When your scanned/image PDF file has been OCR processed and has white background with black text, you can try enabling the OCR temporary solution. This solution will add white rectangular blocks below the translation to cover the original text content.	當您的掃描/圖片版 PDF 文件已進行 OCR 處理，且為白底黑字時，可以嘗試啟用 OCR 版的臨時解決方案。該方案將在譯文下方添加白色矩形塊，以覆蓋原文內容。<br/><br/>若啟用此選項後翻譯非掃描版/圖片版 PDF 文件，可能會丟失部分內容，請在明確是掃描/圖片後再啟用此功能。
babelDoc.answer.saveTime	We will keep your translation records and related documents free of charge for 14 days.<br/>After 14 days, your translation records and documents may be automatically deleted due to system cache clearing and other reasons, and cannot be recovered. Please save or download the necessary files within the validity period to avoid inconvenience.	我們會為您免費保留翻譯記錄及相關文件 14 天。<br/>超過 14 天後，您的翻譯記錄和文件可能會因系統緩存清理等原因被自動刪除，無法恢復。請您在有效期內及時保存或下載所需文件，以免造成不便。
babelDoc.answer.service	All users currently have access to the GLM-4-Flash-250414 model for translation, while Pro users can also choose to use the Qwen-Plus/DeepSeek-V3.2/Doubao-1.5-pro/GPT-5-mini/Gemini-2.5-Flash/Kimi+Qwen/Kimi+DeepSeek/GLM-4.7 models for translation, subject to actual availability. After comparison, we found that Kimi-K2-0905 is effective in extracting terminology, hence we are introducing the "Kimi + Qwen" and "Kimi + DeepSeek" translation services: If you choose the "Kimi + Qwen" translation service and enable automatic terminology extraction, Kimi-K2-0905 will be used to extract terminology, and Qwen-Plus will be used to complete the text translation. All related consumption will be counted towards Qwen usage. (Limited time test) If you choose the "Kimi + DeepSeek" translation service and enable automatic terminology extraction, Kimi-K2-0905 will be used to extract terminology, and DeepSeek-V3.2 will be used to complete the text translation. All related consumption will be counted towards DeepSeek usage. (Limited time test) Since BabelDOC uses a backend translation architecture, all translation logic is executed on the server side, independent of the translation engine used by the plugin. Therefore, the range of translation engines available for BabelDOC differs from those available for immersive translation plugins, and BabelDOC only supports certain advanced translation models, not all advanced models are available.	所有用戶目前均可使用 GLM-4-Flash-250414 模型進行翻譯，而 Pro 用戶還可額外選擇使用 Qwen-Plus/DeepSeek-V3.2/Doubao-1.5-pro/GPT-5-mini/Gemini-2.5-Flash/Kimi+Qwen/Kimi+DeepSeek/GLM-4.7 模型（以實際可選模型為準）進行翻譯。經過對比我們發現 Kimi-K2-0905 提取術語效果較好，因此推出“Kimi + Qwen”和“Kimi + DeepSeek”翻譯服務：若選擇“Kimi + Qwen”翻譯服務，且啟用自動術語提取，則會使用 Kimi-K2-0905 提取術語，並使用 Qwen-Plus 完成文本翻譯。相關消耗均會計入 Qwen 消耗。（限時測試）若選擇“Kimi + DeepSeek”翻譯服務，且啟用自動術語提取，則會使用 Kimi-K2-0905 提取術語，並使用 DeepSeek-V3.2 完成文本翻譯。相關消耗均會計入 DeepSeek 消耗。（限時測試）由於 BabelDOC 採用後端翻譯架構，所有翻譯邏輯均在伺服器端執行，與插件所使用的翻譯引擎相互獨立。因此，BabelDOC 可選用的翻譯引擎範圍與沉浸式翻譯插件存在差異，BabelDOC 僅支持部分高級翻譯模型，並非所有高級模型均可使用。
babelDoc.answer.service.cn	All users can currently use the GLM-4-Flash-250414 model for translation free of charge, while Pro users can also choose to use the Qwen-Plus/DeepSeek-V3.2/Doubao-1.5-pro models for translation.	所有用戶目前均可使用 GLM-4-Flash-250414 模型進行翻譯，而 Pro 用戶還可額外選擇使用 Qwen-Plus/DeepSeek-V3.2/Doubao-1.5-pro/Kimi+Qwen/Kimi+DeepSeek/GLM-4.7 模型（以實際可選模型為準）進行翻譯。經過對比我們發現 Kimi-K2-0905 提取術語效果較好，因此推出“Kimi + Qwen”和“Kimi + DeepSeek”翻譯服務：若選擇“Kimi + Qwen”翻譯服務，且啟用自動術語提取，則會使用 Kimi-K2-0905 提取術語，並使用 Qwen-Plus 完成文本翻譯。相關消耗均會計入 Qwen 消耗。（限時測試）若選擇“Kimi + DeepSeek”翻譯服務，且啟用自動術語提取，則會使用 Kimi-K2-0905 提取術語，並使用 DeepSeek-V3.2 完成文本翻譯。相關消耗均會計入 DeepSeek 消耗。（限時測試）由於 BabelDOC 採用後端翻譯架構，所有翻譯邏輯均在伺服器端執行，與插件所使用的翻譯引擎相互獨立。因此，BabelDOC 可選用的翻譯引擎範圍與沉浸式翻譯插件存在差異，BabelDOC 僅支持部分高級翻譯模型，並非所有高級模型均可使用。
babelDoc.answer.skill	<ol><li><b>Bilingual comparison display:</b> Set the PDF reader to double-page display mode to achieve bilingual comparison reading</li><li><b>Translation Progress Explanation:</b> When generating a PDF file, font subsetting and drawing instruction optimization will be performed, which may take a long time. Please wait patiently</li><li><b>Best practice:</b> It is recommended to test with a small document first, and become familiar with the tool's features before processing large documents</li></ol>	<ol><li><b>雙語對照顯示：</b>將 PDF 閱讀器設置為雙頁顯示模式即可實現雙語對照閱讀</li><li><b>翻譯進度說明：</b>生成 PDF 文件時會進行字體子集化和繪製指令優化，可能需要較長時間，請耐心等待</li><li><b>最佳實踐：</b>建議先用小篇幅文檔測試，熟悉工具特性後再處理大型文檔</li></ol>
babelDoc.answer.slow	Because when exporting a PDF at the end, it is necessary to perform drawing instruction cleanup, which consumes a lot of time, so there will be a lag. Please be patient.	因為在最後導出 PDF 時需要執行繪製指令清理，這個操作需要消耗比較多的時間，所以會出現卡頓的情況。請您耐心等待。
babelDoc.answer.type	<ul><li>Free users have a single translation limit of <b>166</b> pages, while Pro members can translate up to <b>5000</b> pages at a time</li><li>If the page limit is exceeded, you can manually select the translation range (e.g., pages 1-100)</li></ul>	<ul><li>免費用戶單次翻譯上限為 <b>166</b> 頁，Pro 會員單次翻譯上限提升至 <b>5000</b> 頁</li><li>超過頁數限制時，可手動選擇翻譯範圍（如 1-100 頁）</li></ul>
babelDoc.answer.watermark	Currently, removing the watermark is not supported, and we are working to improve it.	當前並不支持去除水印，我們正在努力改進中。
babelDoc.answer.zotero	You can visit the <a href="https://github.com/immersive-translate/zotero-immersivetranslate" target="_blank">Zotero Immersive Translate Plugin</a> repository and install the plugin using the README documentation. (Currently only available to Pro members)	您可以前往 <a href="https://github.com/immersive-translate/zotero-immersivetranslate" target="_blank">Zotero 沉浸式翻譯插件</a> 倉庫，並根據 README 文件說明安裝插件使用。（目前僅 Pro 會員可用）
babelDoc.auto	Auto	自動
babelDoc.availablePages	Remaining available pages this month	本月剩餘可用頁數

Loading…

None

String added in the repository

English

Chinese (Traditional, Hong Kong) 250 characters edited Current translation Translated

BabelDOC 採用並行處理技術，處理速度因文檔特點而異： <ul><li>50 頁左右文檔：通常 1-5 分鐘完成</li><li>500 頁左右文檔：約 10-20 分鐘完成</li><li>1000 頁左右文檔：約 10-20 分鐘完成</li><li>5000 頁左右文檔：約 1-2 小時完成</li><li>處理時間受文檔複雜度、伺服器負載等因素影響</li></ul> 為確保翻譯品質，我們對每個段落進行多重優化處理，包括格式分析、文本提取、翻譯優化等步驟。

2 days ago

Browse all string changes

Things to check

Mismatching line breaks

Number of new lines in translation does not match source

Reset

XML markup

XML tags in translation do not match source

Reset

Glossary

English	Chinese (Traditional, Hong Kong)
No related strings found in the glossary.

String information

Key

babelDoc.answer.performance

String age

2 days ago

Last updated

2 days ago

Source string age

11 months ago

Translation file

app/src/i18n/zh-HK.json, string 624