Ask a Question

Prefer a chat interface with context about you and your work?

Massively Multilingual ASR: 50 Languages, 1 Model, 1 Billion Parameters

Massively Multilingual ASR: 50 Languages, 1 Model, 1 Billion Parameters

We study training a single acoustic model for multiple languages with the aim of improving automatic speech recognition (ASR) performance on low-resource languages, and overall simplifying deployment of ASR systems that support diverse languages.We perform an extensive benchmark on 51 languages, with varying amount of training data by language (from …