wxjiao/ParroT

The ParroT framework to enhance and regulate the Translation Abilities during Chat based on open-sourced LLMs (e.g., LLaMA-7b, Bloomz-7b1-mt) and human written translation and evaluation data.

35
/ 100
Emerging

ParroT helps improve the quality of machine translation, particularly in a chat-like setting, by fine-tuning open-source large language models. You input existing human-translated text, or translation data formatted as instructions with optional 'hints' for specific requirements, and it outputs a more refined, context-aware translation model. This tool is for researchers and language professionals who work with and customize machine translation systems.

176 stars. No commits in the last 6 months.

Use this if you need to train or fine-tune open-source large language models to perform more accurate and contextually appropriate translations, especially for chat-based interactions or when specific translation requirements (hints) are important.

Not ideal if you are looking for a ready-to-use translation application for immediate use, as this project requires technical expertise to set up and train the models.

Machine Translation Natural Language Processing AI Model Customization Language Technology Computational Linguistics
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 17 / 25

How are scores calculated?

Stars

176

Forks

23

Language

Python

License

Last pushed

Dec 31, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/wxjiao/ParroT"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.