rwth-i6/rasr

The RWTH ASR Toolkit.

56
/ 100
Established

This is a comprehensive framework for building and researching automatic speech recognition (ASR) systems. It takes raw audio data and transcribed text as input, processing them to train and evaluate models that can convert spoken language into written text. This tool is designed for speech scientists, researchers, and engineers working on developing new ASR technologies or custom speech applications.

Use this if you are a speech recognition researcher or developer looking for a robust, open-source toolkit to build, customize, or benchmark ASR systems.

Not ideal if you need a ready-to-use, pre-trained speech-to-text service or a simple API for common speech recognition tasks.

speech-recognition voice-technology computational-linguistics acoustic-modeling language-modeling
No Package No Dependents
Maintenance 13 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

58

Forks

17

Language

C++

License

Last pushed

Mar 18, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/rwth-i6/rasr"

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