Robust Speech Recognition via Large-Scale Weak Supervision

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Code for the paper "Language Models are Unsupervised Multitask Learners"

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

This is now the official location of the Merlin project.

Code for the paper "Language Models are Unsupervised Multitask Learners"