Abstract: The autoregressive (AR) models, such as attention-based encoder-decoder models and RNN-Transducer, have achieved great success in speech recognition. They predict the output sequence ...

Abstract: End-to-end automatic speech recognition (E2E-ASR) can be classified by its decoder architectures, such as connectionist temporal classification (CTC), recurrent neural network transducer ...

This repo contains a minimal pytorch implementation of Supervised Memory Training (SMT) and DAgger Memory Training (DMT) for research purposes. The code is simplified for ease of use and modification.

90+ deep learning programs from scratch — ANN, RNN, CNN, Transformers, LSTMs, and AI Agents. Covers neurons to GPT-style decoders with graphical visualizations, real-world datasets (stocks, cancer, ...