State-of-the-art pretrained music models for training, evaluation, inference

Diarization scoring tools.

Code for the AAAI 2022 paper "SSAST: Self-Supervised Audio Spectrogram Transformer".

A concise but complete full-attention transformer with a set of promising experimental features from various papers

Fast audio data augmentation in PyTorch. Inspired by audiomentations. Useful for deep learning.

Self-Supervised Speech Pre-training and Representation Learning Toolkit.

This is the code for the SpeechTokenizer presented in the SpeechTokenizer: Unified Speech Tokenizer for Speech Language Models. Samples are presented on

A command line tool that helps use the "Zero Ressource Challenge" benchmarks

End-to-End Speech Processing Toolkit

Baselines for the Zero-Resources Speech Challenge using VisuallyGrounded Models of Spoken Language, 2021 edition

Phoneme segmentation using pre-trained speech models

A curated list of awesome self-supervised methods

Easy to use scripts for evaluating word vectors on a variety of tasks.

Competition for best expository article on cutting-edge ML research

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.