LibreASR logo


An On-Premises, Streaming Speech Recognition System
+ 1

What is LibreASR?

It is an On-Premises, Streaming Speech Recognition System built with PyTorch and fastai.
LibreASR is a tool in the Speech Recognition Tools category of a tech stack.
LibreASR is an open source tool with 664 GitHub stars and 29 GitHub forks. Here’s a link to LibreASR's open source repository on GitHub

Who uses LibreASR?


LibreASR's Features

  • RNN-T network
  • Fused language models
  • Dynamic Bucketing DataLoader
  • Dynamic Quantization
  • Tuned language model fusion

LibreASR Alternatives & Comparisons

What are some alternatives to LibreASR?
It is a state-of-the-art automatic speech recognition toolkit. It is intended for use by speech recognition researchers and professionals.
Botium Speech Processing
It is a unified, developer-friendly API to the best available Speech-To-Text and Text-To-Speech services.
It can be used to complement any regular touch user interface with a real time voice user interface. It offers real time feedback for faster and more intuitive experience that enables end user to recover from possible errors quickly and with no interruptions.
wav2letter++ is a fast open source speech processing toolkit from the Speech Team at Facebook AI Research. It is written entirely in C++ and uses the ArrayFire tensor library and the flashlight machine learning library for maximum efficiency. Our approach is detailed in this arXiv paper.
It is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.
See all alternatives
Related Comparisons
No related comparisons found

LibreASR's Followers
3 developers follow LibreASR to keep up with related blogs and decisions.