MTEB: State-of-the-art evaluation of embeddings across languages and modalities

[ICASSP'26] Real-time streaming voice anonymization & voice conversion

A structured approach to PhD thesis preparation and writing

Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities. ACM Computing Surveys, 2026.

ARCH: Audio Representations benCHmark

Self-Supervised Speech Pre-training and Representation Learning Toolkit

A collection of extensions and data-loaders for few-shot learning & meta-learning in PyTorch

Allosaurus is a pretrained universal phone recognizer for more than 2000 languages

The PyTorch-based audio source separation toolkit for researchers

🛁 Clean Code concepts adapted for Python

PRML algorithms implemented in Python

[ICLR 2020] NAS evaluation is frustratingly hard

🔊 A comprehensive list of open-source datasets for voice and sound computing (95+ datasets).

Tutorial: Graph Neural Networks for Natural Language Processing at EMNLP 2019 and CODS-COMAD 2020

PyTorch implementation of "Efficient Neural Architecture Search via Parameters Sharing"

pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding a…

A complete computer science study plan to become a software engineer.