ictnlp/LSG

The code for AAAI 2025 “Large Language Models Are Read/Write Policy-Makers for Simultaneous Generation”

27
/ 100
Experimental

This project helps with real-time translation and transcription by efficiently processing audio or text streams as they arrive, rather than waiting for an entire input to finish. It takes live audio or text in one language and produces translated text or transcribed speech in another, or the same, language simultaneously. This is ideal for professional translators, live captioning providers, or anyone needing immediate understanding of spoken or written content in different languages.

No commits in the last 6 months.

Use this if you need to translate or transcribe spoken or written content in real-time, providing immediate output as the input stream progresses.

Not ideal if you need a simple, offline translation for static, complete texts or audio files where latency is not a concern.

simultaneous-translation live-captioning speech-to-text real-time-transcription language-interpretation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 5 / 25

How are scores calculated?

Stars

15

Forks

1

Language

Python

License

CC-BY-SA-4.0

Last pushed

Jan 03, 2025

Commits (30d)

0

Get this data via API

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

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