Leonardo Pepino's starred repositories
VisionMamba
Implementation of Vision Mamba from the paper: "Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model" It's 2.8x faster than DeiT and saves 86.8% GPU memory when performing batch inference to extract features on high-res images
conformal-predictions-from-scratch
Various Conformal Prediction methods implemented from scratch in pure NumPy for an educational purpose.
frechet-audio-distance
A lightweight library for Frechet Audio Distance calculation.
transformer-contributions
Measuring the Mixing of Contextual Information in the Transformer
Fermat-distance
We propose a density-based estimator for weighted geodesic distances suitable for data lying on a manifold of lower dimension than ambient space and sampled from a possibly nonuniform distribution
plla-tisvs
Phoneme Level Lyrics Alignment and Text-Informed Singing Voice Separation
Lyrics-to-Audio-Alignment
Aligns text (lyrics) with monophonic singing voice (audio). The algorithm uses structural segmentation to segment the audio into structures and then uses hidden markov models to obtain alignment within segments. The final alignment is concatenation of time stamps of lyrics within the segments for each song.
flash-attention
Fast and memory-efficient exact attention
ColossalAI
Making large AI models cheaper, faster and more accessible
libri-light
dataset for lightly supervised training using the librivox audio book recordings. https://librivox.org/.
layerwise-analysis
Layer-wise analysis of self-supervised pre-trained speech representations
pytorch-dann
A PyTorch implementation for Unsupervised Domain Adaptation by Backpropagation
listening-test
An open source platform for browser based speech and audio subjective quality tests.
google-research
Google Research
FullSubNet
PyTorch implementation of "FullSubNet: A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancement."
rotary-embedding-torch
Implementation of Rotary Embeddings, from the Roformer paper, in Pytorch