GeezerVison

Self-Supervised Speech Pre-training and Representation Learning Toolkit

End-to-End Speech Processing Toolkit (Fork to ensure S3PRL works on ESPNet)

LightHuBERT: Lightweight and Configurable Speech Representation Learning with Once-for-All Hidden-Unit BERT

Extensions to YAML syntax for better python interaction

An open source dataset for source separation

Code for DeCoAR (ICASSP 2020) and BERTphone (Odyssey 2020)

Non-Autoregressive Predictive Coding

This is an open source project (formerly named Listen, Attend and Spell - PyTorch Implementation) for end-to-end ASR implemented with Pytorch, the well known deep learning toolkit.