A library built for easier audio self-supervised training, downstream tasks evaluation

The official repository of Dynamic-SUPERB.

This Repository surveys the paper focusing on Prompting and Adapters for Speech Processing.

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Audio Codec Speech processing Universal PERformance Benchmark

[Research] Code and artifacts for the papers related to RobustDistiller (Robust and Efficient S3RL models)

Code for the Interspeech 2021 paper "AST: Audio Spectrogram Transformer".

TorchEEG is a library built on PyTorch for EEG signal analysis.

A library for experimenting with, training and evaluating neural networks, with a focus on adversarial robustness.

This repository contains the SpeechBrain Benchmarks

Fast and memory-efficient exact attention

《SpeechPrompt v2: Prompt Tuning for Speech Classification Tasks》Speech processing with prompting paradigm

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

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

INTERSPEECH 2023: "DPHuBERT: Joint Distillation and Pruning of Self-Supervised Speech Models"

FitHuBERT: Going Thinner and Deeper for Knowledge Distillation of Speech Self-Supervised Learning (INTERSPEECH 2022)

Awesome Knowledge-Distillation. 分类整理的知识蒸馏paper(2014-2021)。

Making large AI models cheaper, faster and more accessible

Implementation of Nougat Neural Optical Understanding for Academic Documents

A framework for generating labeled audio recordings of single-spoken keywords via automatic forced alignment.

ICASSP 2023-2024 Papers: A complete collection of influential and exciting research papers from the ICASSP 2023-24 conferences. Explore the latest advancements in acoustics, speech and signal proce…

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

JUCE is an open-source cross-platform C++ application framework for desktop and mobile applications, including VST, VST3, AU, AUv3, LV2 and AAX audio plug-ins.

A collection of papers related to speech model compression

Inference Llama 2 in one file of pure C

Defending against Adversarial Audio via Diffusion Model (ICLR 2023)

A Pytorch Knowledge Distillation library for benchmarking and extending works in the domains of Knowledge Distillation, Pruning, and Quantization.

Collection of recent methods on (deep) neural network compression and acceleration.

RobustBench: a standardized adversarial robustness benchmark [NeurIPS'21 Benchmarks and Datasets Track]