What shall we do with an hour of data? Speech recognition for the un- and under-served languages of Common Voice

• Main Authors: Tyers, Francis M, Meyer, Josh
• Format: Journal Article
• Language: English
• Published: 10-05-2021
• Subjects: Computer Science - Computation and Language; Computer Science - Learning; Computer Science - Sound
• DOI: 10.48550/arxiv.2105.04674

This technical report describes the methods and results of a three-week
sprint to produce deployable speech recognition models for 31 under-served
languages of the Common Voice project. We outline the preprocessing steps,
hyperparameter selection, and resulting accuracy on official testing sets. In
addition to this we evaluate the models on multiple tasks: closed-vocabulary
speech recognition, pre-transcription, forced alignment, and key-word spotting.
The following experiments use Coqui STT, a toolkit for training and deployment
of neural Speech-to-Text models.