Francis McCann

Deep Learning Researcher at AssemblyAI

Conformer-2: a state-of-the-art speech recognition model trained on 1.1M hours of data

Launch

Jul 19, 2023

Conformer-2: a state-of-the-art speech recognition model trained on 1.1M hours of data

We're introducing Conformer-2, our latest AI model for automatic speech recognition. Conformer-2 is trained on 1.1M hours of English audio data, extending Conformer-1 to provide improvements on proper nouns, alphanumerics, and robustness to noise.

Francis McCann

Deep Learning Researcher at AssemblyAI

Deep Learning

Jun 8, 2022

Review - Decision Transformer & SPIRAL

This week’s Deep Learning Paper Review is Decision Transformer: Reinforcement Learning via Sequence Modeling and SPIRAL: Self-supervised Perturbation-Invariant Representation Learning for Speech Pre-Training

Kevin Zhang, Francis McCann

Deep Learning Researcher at AssemblyAI, Deep Learning Researcher at AssemblyAI