https://github.com/devinit/large-pdf-llm-translate

Chunk and translate large PDFs using LLMs
https://github.com/devinit/large-pdf-llm-translate

Last synced: about 1 year ago
JSON representation

Chunk and translate large PDFs using LLMs

• Host: GitHub
• URL: https://github.com/devinit/large-pdf-llm-translate
• Owner: devinit
• License: apache-2.0
• Created: 2024-09-11T11:59:47.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2024-09-11T15:45:14.000Z (over 1 year ago)
• Last Synced: 2025-01-07T21:45:01.574Z (about 1 year ago)
• Language: Python
• Size: 2.89 MB
• Stars: 0
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# large-pdf-llm-translate

Chunk and translate large PDFs using LLMs

## Installation

```

python3 -m virtualenv venv

source venv/bin/activate

pip install -r requirements.txt

```

## To run

```

rm -rf pdfs_tmp

rm -rf output

python3 code/split_pdf.py pdfs/240607021743.pdf

python3 code/translate_pdfs.py

```