LibreASR
LibreASR copied to clipboard
iceychris
:speech_balloon: An On-Premises, Streaming Speech Recognition System
Hello, really nice project, I am thoroughly impressed. However, in my humble opinion the project needs an AUR package in order to reach its full potential and address its target...
Design a logo for LibreASR and share it here. To make an open source project cool, it should have a logo :smile:
The [HN discussion](https://news.ycombinator.com/item?id=25099847) brought up a few ways to improve the recognition performance. Some of those are: * [teacher-student training](https://news.ycombinator.com/item?id=25106628) * [pre-training the encoder network](https://news.ycombinator.com/item?id=25100212) as in [wav2vec](https://ai.facebook.com/blog/wav2vec-20-learning-the-structure-of-speech-from-raw-audio/) Look into...
[As HN user `sagz` suggested](https://news.ycombinator.com/item?id=25105466), look into using the [Live Transcribe Android App](https://github.com/google/live-transcribe-speech-engine) with LibreASR. This would be great for deaf and hard of hearing people.
Make LibreASR work on [Raspberry Pis](https://www.raspberrypi.org/). There already is a [Dockerfile](https://github.com/iceychris/LibreASR/blob/master/docker/Dockerfile.armv7) which builds fine on my Pi 4. Loading and running the PyTorch models also works. But, loading the [youtokentome](https://github.com/VKCOM/YouTokenToMe)...