@solyarisoftware/voskjs
Version:
NodeJs developers API for Vosk-api speech-to-text engine.
8 lines (6 loc) • 340 B
Plain Text
All audio from LibriSpeech[1], a corpus of approximately 1000 hours of 16 kHz
read English speech, prepared by Vassil Panayotov with the assistance of Daniel
Povey. The data is derived from read audiobooks from the LibriVox project[2],
and has been carefully segmented and aligned.
[] http://www.openslr.org/12
[] https://librivox.org/