swasun

FCN-KAN

Kolmogorov–Arnold Networks with modified activation (using fully connected network to represent the activation)

pykan

Kolmogorov Arnold Networks

soundata

Python library for downloading, loading & working with sound datasets

RTD_AE

This is an official repository for "Learning topology-preserving data representations" presented at ICLR 2023 conference.

TopoModelX

Topological Deep Learning

awesome-topological-deep-learning

A curated list of topological deep learning (TDL) resources and links.

ibsgd

speechbrain

A PyTorch-based Speech Toolkit

MindVideo

naturalspeech2-pytorch

Implementation of Natural Speech 2, Zero-shot Speech and Singing Synthesizer, in Pytorch

neuroethology_paper_2021

for 2021 current opinions paper

ImageBind

ImageBind One Embedding Space to Bind Them All

brain2gan

DeepPhonemizer

Grapheme to phoneme conversion with deep learning.

xpinyin

Translate Chinese hanzi to pinyin (拼音) by Python, 汉字转拼音

commonvoice-utils

Linguistic processing for Common Voice

TranSpeech

PyTorch Implementation of TranSpeech (ICLR'23): Textless NAR Speech-to-Speech Translation with Bilateral Perturbation

GenerSpeech

PyTorch Implementation of GenerSpeech (NeurIPS'22): a text-to-speech model towards zero-shot style transfer of OOD custom voice.

torchlens

Package for extracting and mapping the results of every single tensor operation in a PyTorch model in one line of code.

Multilingual-PR

Phoneme Recognition using pre-trained models Wav2vec2, HuBERT and WavLM. Throughout this project, we compared specifically three different self-supervised models, Wav2vec (2019, 2020), HuBERT (2021) and WavLM (2022) pretrained on a corpus of English speech that we will use in various ways to perform phoneme recognition for different languages with a network trained with Connectionist Temporal Classification (CTC) algorithm.

thingsvision

Python package for extracting representations from state-of-the-art computer vision models

frrsa

Python package to conduct feature-reweighted representational similarity analysis.

simple-speech-features

Simple, straight-forward extraction of acoustic and prosodic features from sound waves based on Praat and Parselmouth.

mind-vis

Code base for MinD-Vis

unilm

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

openai-cookbook

Examples and guides for using the OpenAI API

LaPreprint

📝 A nicely formatted LaTeX preprint template

SincNet

SincNet is a neural architecture for efficiently processing raw audio samples.

bert-brains

summit