OSU-STARLAB/Simul-LLM

[ACL 2024] An easily extensible framework for simultaneous, text-to-text neural machine translation (SimulMT) for LLMs.

36
/ 100
Emerging

This framework helps machine translation researchers and developers build and evaluate custom large language models for simultaneous translation. You provide text in one language, and it translates into another language almost instantly, without waiting for the full sentence. It's used by researchers and engineers developing next-generation real-time translation systems.

No commits in the last 6 months.

Use this if you are a researcher or developer working on advanced simultaneous machine translation models and need a flexible pipeline to fine-tune and evaluate LLMs for this specific task.

Not ideal if you're an end-user looking for a ready-to-use real-time translation application; this is a development tool, not a finished product.

simultaneous translation neural machine translation LLM fine-tuning real-time language processing computational linguistics
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

18

Forks

3

Language

Python

License

MIT

Last pushed

Apr 21, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/OSU-STARLAB/Simul-LLM"

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