A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

Some fast-ish algorithms for batch text search in moderate-sized collections, intended for data cleanup

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

Kaldi style neural network training in pytorch for use in place of nnet3 in Kaldi.

Espresso: A Fast End-to-End Neural Speech Recognition Toolkit

This is now the official location of the Kaldi project.

This is not the official kaldi repository. It is better to fork https://github.com/kaldi-asr/kaldi or https://github.com/vimalmanohar/kaldi instead.