GPU-Accelerated WFST Beam Search Decoder for CTC-based Speech Recognition

1 code implementation • 8 Nov 2023 • Daniel Galvez, Tim Kaldewey

While Connectionist Temporal Classification (CTC) models deliver state-of-the-art accuracy in automated speech recognition (ASR) pipelines, their performance has been limited by CPU-based beam search decoding.

speech-recognition Speech Recognition

A Data-Centric Approach for Training Deep Neural Networks with Less Data

no code implementations • 7 Oct 2021 • Mohammad Motamedi, Nikolay Sakharnykh, Tim Kaldewey

While the availability of large datasets is perceived to be a key requirement for training deep neural networks, it is possible to train such models with relatively little data.

GPU-Accelerated Viterbi Exact Lattice Decoder for Batched Online and Offline Speech Recognition

1 code implementation • 22 Oct 2019 • Hugo Braun, Justin Luitjens, Ryan Leary, Tim Kaldewey, Daniel Povey

We present an optimized weighted finite-state transducer (WFST) decoder capable of online streaming and offline batch processing of audio using Graphics Processing Units (GPUs).

speech-recognition Speech Recognition