George0828Zhang/simulst

PyTorch toolkit for streaming speech recognition, speech translation and simultaneous translation based on fairseq.

28
/ 100
Experimental

This project provides advanced models and tools for developing real-time speech translation and recognition systems. It takes live audio input and rapidly converts it into transcribed text or translated text in another language. This is ideal for researchers and engineers working on conversational AI, live captioning, or immediate cross-language communication applications.

No commits in the last 6 months.

Use this if you are a researcher or developer focused on building or improving systems that need to translate or transcribe speech as it is being spoken.

Not ideal if you are looking for an out-of-the-box application for end-users rather than a toolkit for system development.

speech-to-text speech-translation real-time-transcription natural-language-processing conversational-ai
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 13 / 25

How are scores calculated?

Stars

25

Forks

4

Language

Python

License

Last pushed

Oct 03, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/George0828Zhang/simulst"

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