Wed, 22 Jun 2022 09:13:48 GMT 2022-06-22T09:13:48Z <p class="fragment">DigiEduBerlin team is happy to announce that first release of a small but powerful open-source automatic speech recognition (ASR) package "lesen-mikroserver" which is, from now on, available on Github here: <a href="https://github.com/hromi/lesen-mikroserver" target="_blank" rel="noopener">https://github.com/hromi/lesen-mikroserver</a>.</p> <p class="fragment">lesen-mikroserver is based on code from wonderful <a href="https://coqui.ai/" target="_blank" rel="noopener">coqui</a> speech-to-text (STT). server-side component of "lesen-mikroserver" is able to run inferences on 512-Volta tensor cores of Xavier Jetson Dev Kit GPUs devices and will be used exhaustively in the context of <a href="https://lesen.digital">lesen.digital</a> and <a href="https://fibel.digital">fibel.digital</a> projects.</p> <p class="fragment">Note also our small but tidy <a href="https://github.com/hromi/lesen-mikroserver/blob/main/client/client.html" target="_blank" rel="noopener">getUserMedia -> mediaRecorder -> Websocket -> Jetson -> Browser client</a> which is more or less all You need to bring state of the art ASR / STT in Your pupil's browsers.</p> Info