Fast and differentiable hidden Markov model in C++

Unsupervised phone and word segmentation using dynamic programming on self-supervised VQ features.

kaldi-asr/kaldi is the official location of the Kaldi project.

DinoSR: Self-Distillation and Online Clustering for Self-supervised Speech Representation Learning

Free, open-source Chinese character data

This code corresponds to our ICML paper titled "Representer Point Selection for Explaining Regularized High-dimensional Models".

Python re-implementation of the (constrained) spectral clustering algorithms used in Google's speaker diarization papers.

Using embedding-based loss functions for phonetics/speech recognition.

An ASR toolkit with the freedom of topology

程序员延寿指南 | A programmer's guide to live longer

MLNLP社区用来帮助大家避免论文投稿小错误的整理仓库。 Paper Writing Tips

List of Computer Science courses with video lectures.

A Non-Autoregressive Transformer based Text-to-Speech, supporting a family of SOTA transformers with supervised and unsupervised duration modelings. This project grows with the research community, …

End-to-End Speech Processing Toolkit

🎓 Path to a free self-taught education in Computer Science!

PyTorch CTC Decoder bindings

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

Attempt at tracking states of the arts and recent results (bibliography) on speech recognition.