TharinduDR/TransQuest

Transformer based translation quality estimation

52
/ 100
Established

This tool helps you automatically assess the quality of machine translations without needing a perfect reference translation. You input a source text and its machine-translated version, and it tells you how good the translation is, either for the whole sentence or word-by-word. This is for translation project managers, content creators, or anyone relying on machine translation for various languages.

114 stars. No commits in the last 6 months. Available on PyPI.

Use this if you need to quickly check the reliability of machine-translated content, decide if it needs human review, or pick the best translation from multiple options.

Not ideal if you already have a perfect human translation to compare against, or if you need to translate content yourself rather than evaluate existing translations.

machine-translation translation-quality-control localization content-publishing language-services
Stale 6m
Maintenance 0 / 25
Adoption 9 / 25
Maturity 25 / 25
Community 18 / 25

How are scores calculated?

Stars

114

Forks

20

Language

Python

License

Apache-2.0

Last pushed

Jul 20, 2023

Commits (30d)

0

Dependencies

15

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/TharinduDR/TransQuest"

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