Quotation_identification_BERT.v1

📚 Quote Identifier

A program that identifies quotes in text documents using a BERT-based model. 🤖

🛠️ Requirements

• Python 3.10 🐍
• pip (Python package installer) 📦

🚀 Installation

1. Clone this repository:

git clone https://huggingface.co/drewThomasson/Quotation_identification_BERT.v1
cd Quotation_identification_BERT.v1

1. Install the required packages:

pip install pandas torch transformers tqdm

💡 Note: If you have a CUDA-capable GPU, visit https://pytorch.org for the appropriate PyTorch installation command.

🏃‍♂️ Usage

Run the program with:

python Metal_gui_original_quotation_identification_BERT_infrence.py

GUI Instructions:

1. 📂 Click "Open Text File" to select your text file.
2. 🔍 Click "Identify Quotes" to process the file.
3. 🖥️ A new window will open showing the text with identified quotes highlighted.

📁 Included Files

• quote_identifier.py: Main Python script 🐍
• quotation_identifer_model/: Directory containing the pre-trained model 🧠
  • checkpoint-1000/: Model checkpoint ✅
• sample_book.txt: Sample text file for testing 📘

🤗 Hugging Face Repository Contents

1. Pre-trained quote identification model 🧠
2. sample_book.txt 📘
3. quote_identifier.py script 🐍
4. This README 📄

📝 Notes

• Ensure the local model directory ./quotation_identifer_model/checkpoint-1000/ is present.
• The program creates a BERT_infrence_quote_input.csv file when processing text.
• 🌓 Use the "Toggle Dark Mode" button to switch between light and dark themes.

🆘 Troubleshooting

If you encounter issues:

1. 📦 Verify all required packages are correctly installed.
2. 🗂️ Check that the model directory is present with necessary files.
3. 🐍 Confirm you're using Python 3.10.