ictnlp/SiLLM

SiLLM is a Simultaneous Machine Translation (SiMT) Framework. It utilizes a Large Language model as the translation model and employs a traditional SiMT model for policy-decision to achieve SiMT through collaboration.

23
/ 100
Experimental

This project helps researchers and developers working in natural language processing to build and experiment with simultaneous machine translation systems. It takes an existing Large Language Model and pairs it with traditional simultaneous translation techniques to produce real-time, streaming translations of spoken or written input. Researchers can use this to explore advanced methods for translating languages on the fly.

No commits in the last 6 months.

Use this if you are an NLP researcher or developer focusing on creating or improving real-time, simultaneous translation systems.

Not ideal if you need a ready-to-use translation application for end-users, as this is a research framework for building such systems.

natural-language-processing machine-translation simultaneous-translation large-language-models speech-to-text
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 9 / 25

How are scores calculated?

Stars

18

Forks

2

Language

Python

License

Last pushed

Feb 22, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/ictnlp/SiLLM"

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