The number of end-to-end speech recognition models grows every year. The...
We propose an end-to-end ASR system that can be trained on transcribed s...
Automatic speech recognition models are often adapted to improve their
a...
In this paper, we introduce a new toolbox for constructing speech datase...
In the English speech-to-text (STT) machine learning task, acoustic mode...
NeMo (Neural Modules) is a Python framework-agnostic toolkit for creatin...
We propose NovoGrad, a first-order stochastic gradient method with layer...
In this paper, we report state-of-the-art results on LibriSpeech among
e...
Building an accurate automatic speech recognition (ASR) system requires ...
We present OpenSeq2Seq -- an open-source toolkit for training
sequence-t...