Transform Your Medical Lectures Into Smart Scripts: Accuracy Meets Efficiency

An automation tool that converts lecture recordings into scripts and summaries. Unlike similar services like Naver Clova Note and Daglo, our software offers unique features tailored for medical education. It translates all medical terminology into English and eliminates filler words and stutters.

For example:

• Original: "3번은 닉몬이야. 그래서 폐렴이라고 하는 거는"
  Processed: "3위는 Pneumonia입니다. 그래서 Pneumonia이"

• Original: "이 암이라는 것은 mmr살프로리퍼레이션 서브와이블 때문에 생기는 질환이에요."
  Processed: "Cancer는 주로 MMR (Mismatch Repair) 때문에 발생하는 disease입니다."

The summaries generated are succinct and accurate, and even include a content review quiz.

• Overview
• Prerequisites
• Configuration
• How it Works
  • File Scanning
  • Text Processing
  • File Movement
  • Error Handling
• Usage
• Customization Options
• Directory Structure
• File Naming Convention
• Contributors
• Contact

This Python script automatically processes raw text files by correcting errors, translating to English, summarizing the content, and converting it to a Word document.

• Python 3.x
• OpenAI API Key
• Following Python packages:
  • python-dotenv
  • openai
  • docx

Run the following commands to install the necessary packages:

pip install python-dotenv openai docx

1. Create a .env file in the root directory and add your OpenAI API Key:

   OPEN_API_KEY=your-api-key
   

2. Update the raw_root_dir variable with your actual root directory path for raw text files.

The function get_txt_files scans the raw_root_dir for all .txt files.

raw_text_to_product performs multiple operations on each text file:

• Correction
• Translation to English
• Summarization

After processing, the raw text file is moved to the used_raw_root_dir.

The script retries up to 5 times if any errors are encountered.

Run the txt_to_product.ipynb to start the automated process. It will process all raw text files in the raw_root_dir.

• Location of Raw Files: The location specified by raw_root_dir in txt_to_product.ipynb can be changed according to your needs.
• File Organization: After the script and summary are generated, they can be organized using OrganizeFiles.ipynb.

• Raw files: Placed in raw_root_dir
• Processed files: Moved to used_raw_root_dir
• Intermediate and final products: Stored in intermediate, englished, and summary directories

Raw text files must follow this naming convention: raw_subject_week_day_numb.txt

• LEE KYEONGEON
• KIM TAEHONG

For any questions or further information, feel free to reach out at [email protected].