Skip to content

kau10082/transcript-fix

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

11 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

transcript-fix

把醫學演講/會議的「語音轉文字」逐字稿整理乾淨 —— 修好被聽錯的藥名和數字,而且絕不亂編。

Clean up the messy voice-to-text transcripts of medical talks — fix the misheard drug names and numbers, and never make anything up.


1. 專案簡介 · About The Project

這是一個 Claudeskill(技能)。你把演講錄音跑「語音轉文字(ASR)」之後,常會得到一份藥名、試驗名、數字被聽錯的稿子;這個 skill 就是專門幫你把它小心地修好、重寫成乾淨又正確的中文。

This is a Claude skill. After you run a talk's audio through voice-to-text (ASR), you often get a transcript with misheard drug names, trial names, and numbers. This skill carefully fixes those and rewrites the text into something clean and correct.

它最重要的一條原則是:不確定的東西,就老實標出來,絕不假裝很確定

Its most important rule is simple: if it isn't sure, it says so — it never pretends to be certain.


2. 最新更新 · What's New

2026-07(最近一次更新)

2026-07 (latest update)

  • 🛡️ 詞庫防呆強化:只有「你親自點頭確認」或「查文獻證實」的更正,才會被存回詞庫;單純多份稿一致不算數,避免把「一起聽錯」的內容當成正確答案存起來。 🛡️ Safer glossary: only corrections you've personally confirmed (or verified against the literature) get saved back — multiple transcripts merely agreeing is not enough, so a shared mistake never gets saved as truth.
  • 🔁 多稿比對:現在支援一次比對多份逐字稿(2–4 份最佳),用「多數決」找出真正的疑點。 🔁 Multi-transcript compare: you can now compare several transcripts at once (2–4 is ideal) and let the majority decide the tricky spots.
  • 🌐 沒有 Notion 也能用:連不上詞庫時會自動略過、繼續整理,不會卡住。 🌐 Works without Notion: if the glossary can't be reached, it just skips that step and carries on instead of getting stuck.
  • 📄 雙語 README + MIT 授權:文件全面白話化,並加上開源授權。 📄 Bilingual README + MIT license: docs rewritten in plain language, and an open-source license added.

3. 為什麼要用這個專案? · Why Choose This?

① 絕不亂編,安全第一

① It never fabricates — safety first

它不會替任何「無法確認的資訊」硬填答案(人名、藥名、數字、劑量都一樣),也不會捏造文獻引用。不確定的地方會清楚標記,讓你一眼看到哪裡還要再確認。

It won't fill in anything it can't confirm (names, drugs, numbers, doses alike), and it won't invent citations. Anything uncertain is clearly flagged, so you can see at a glance what still needs checking.

② 有一個會越用越聰明的詞庫

② It has a word list that gets smarter the more you use it

你可以在自己的 Notion 建一份「這個字常被聽成那個」的對照表。每整理完一份稿,新學到的更正就會存回去,下一次同類主題的稿子就更好整理。

You can keep a "this-gets-heard-as-that" list in your own Notion. After each job, new confirmed corrections are saved back, so the next transcript on a similar topic is even easier.

③ 用起來很省事

③ It's easy to use

你不用學任何指令或操作介面。只要把稿子丟給 Claude、用白話說「幫我校稿」,它就會自動開始跑整個流程。

There's nothing to learn — no commands, no interface. Just hand Claude the transcript and say, in plain words, "help me proofread this," and it runs the whole process for you.


4. 快速開始 · Getting Started

請照下面的步驟安裝。

Follow these steps to install.

# 1. 下載專案 / Download the project
git clone https://github.com/kau10082/transcript-fix.git

# 2. 把整個資料夾放到 Claude 的 skills 位置
#    Move the whole folder into your Claude skills location
#    例如 / e.g. /skills/user/transcript-fix/

# 3. (可選)設定你自己的詞庫 / (Optional) set up your own glossary
cp config.example.json config.local.json
#    接著打開 config.local.json,填入你的 Notion ID
#    then open config.local.json and fill in your Notion IDs

關於 Notion(可選):詞庫功能需要在 Claude 裡連上 Notion 連接器(在 Claude App 的「Connectors/連接器」設定裡按 Notion → 授權即可,不需要 API key)。不想用詞庫也沒關係,skill 照樣能運作。

About Notion (optional): the glossary needs the Notion connector in Claude (open Connectors in the Claude app, click Notion, and authorize — no API key needed). Don't want the glossary? That's fine, the skill still works without it.


5. 基本使用方式 · Usage

安裝好之後,使用方法非常簡單:在 Claude 對話中丟給它一份醫學逐字稿,然後用白話講出你的需求就好。

Once installed, using it is very simple: in a Claude conversation, give it a medical transcript and just say what you want in plain words.

可以這樣說(任一句都會觸發):

You can say things like (any of these will trigger it):

  • 「幫我校稿這份逐字稿」/ "Help me proofread this transcript"
  • 「把這份演講的逐字稿整理乾淨」/ "Clean up this lecture transcript"
  • 「幫我做語意重建」/ "Do a semantic reconstruction for me"
  • 「這是同一場的另一份逐字稿,幫我對照」/ "Here's another transcript of the same talk — compare them for me"

整理完你會拿到兩份檔案:一份是清乾淨的逐字稿,另一份是「還需要再確認的事項」清單。

When it's done you'll get two files: a cleaned-up transcript, and a checklist of things still worth double-checking.


6. 目錄結構 · Repository Structure

transcript-fix/
├── SKILL.md              # 核心:skill 的完整流程與規則 / The skill's full workflow and rules
├── README.md             # 就是你正在讀的這份說明 / The document you're reading now
├── config.example.json   # 設定範本,供你複製 / A config template for you to copy
├── config.local.json     # 你的私人 Notion 設定(本機、不會上傳)/ Your private Notion settings (local, never uploaded)
├── .gitignore            # 指定哪些檔案不上傳 / Tells git which files to keep out
└── LICENSE               # 授權條款 / The license

各檔案的作用,白話說明如下:

Here's what each file does, in plain terms:

  • SKILL.md:整個 skill 的大腦,寫著它該怎麼一步步整理稿子。這是最重要的檔案。 SKILL.md: the brain of the skill — it spells out exactly how to clean up a transcript step by step. This is the most important file.
  • config.example.json:設定的「範本」。你把它複製成 config.local.json 再填入自己的資料。 config.example.json: a settings template. You copy it to config.local.json and fill in your own details.
  • config.local.json:你的私人設定(Notion 詞庫位置)。它只留在你電腦上,永遠不會被上傳,所以你的資料很安全。 config.local.json: your private settings (where your Notion glossary is). It stays on your computer and is never uploaded, so your data stays safe.

7. 貢獻指南 · Contributing

非常歡迎你一起讓這個專案變得更好!不管是修正錯字、改善流程,還是回報問題,都很感謝。

Contributions are very welcome — thank you for helping make this project better! Whether it's fixing a typo, improving the workflow, or reporting a problem, it all helps.

想改程式碼(送出修改):

Want to change something (submit an edit):

  1. Fork 這個專案到你自己的帳號。/ Fork this project to your own account.
  2. 建一個新的分支來做修改。/ Create a new branch for your changes.
  3. 改好之後,發一個 Pull Request(PR) 過來,簡單說明你改了什麼。/ When you're done, open a Pull Request (PR) and briefly describe what you changed.

只是想回報問題或提想法:

Just want to report a problem or share an idea:

直接到 Issues 頁面 開一則 Issue,用白話描述你遇到的狀況就可以了。

Just open an issue on the Issues page and describe what you ran into in plain words.


8. 授權條款 · License

本專案採用 MIT 授權。簡單來說:你可以自由使用、修改、分享,甚至用在商業用途,唯一的條件是保留原本的授權與版權聲明(也就是標示出處)。

This project uses the MIT License. In short: you're free to use, modify, share, and even use it commercially — the only condition is that you keep the original license and copyright notice (i.e. credit the source).

完整條款請見 LICENSE 檔案。

See the LICENSE file for the full terms.


由 Claude 協作打造。 / Built with Claude.

About

Claude skill to proofread & semantically reconstruct error-dense medical ASR transcripts — multi-transcript diff, never fabricates, powered by a self-growing Notion glossary that learns confusing terms automatically. | 醫學語音逐字稿校稿與語意重建的 Claude skill:多稿交叉比對、絕不捏造,搭配「會自動記錄易混淆字詞、自我成長」的 Notion 詞庫。

Topics

Resources

License

Stars

0 stars

Watchers

0 watching

Forks

Releases

No releases published

Packages

 
 
 

Contributors