Leonardo Pepino's starred repositories
pytorch-image-models
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
ffmpeg-python
Python bindings for FFmpeg - with complex filtering support
pedalboard
🎛 🔊 A Python library for audio.
x-transformers
A simple but complete full-attention transformer with a set of promising experimental features from various papers
OpenPrompt
An Open-Source Framework for Prompt-Learning.
textdistance
📐 Compute distance between sequences. 30+ algorithms, pure python implementation, common interface, optional external libs usage.
promptsource
Toolkit for creating, sharing and using natural language prompts.
FastSpeech2
An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"
performer-pytorch
An implementation of Performer, a linear attention-based transformer, in Pytorch
cleanthesis
Clean Thesis is a clean, simple, and elegant LaTeX style (or template) for thesis documents.
GST-Tacotron
A PyTorch implementation of Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis
lyrebird-wav2clip
Official implementation of the paper WAV2CLIP: LEARNING ROBUST AUDIO REPRESENTATIONS FROM CLIP
hifigan-denoiser
HiFi-GAN: High Fidelity Denoising and Dereverberation Based on Speech Deep Features in Adversarial Networks
Catch-A-Waveform
Official pytorch implementation of the paper: "Catch-A-Waveform: Learning to Generate Audio from a Single Short Example" (NeurIPS 2021)
ltspice-guitar-pedals
A collection of LTSpice simulation files for popular guitar effects. :guitar: :electron: :musical_note: :chart_with_upwards_trend: Pull requests welcome :smiley:
PyTorch-Raspberry-Pi-64-OS
PyTorch installation wheels for Raspberry Pi 64 OS
simple-speaker-embedding
A speaker embedding network in Pytorch that is very quick to set up and use for whatever purposes.
CLEAR-dataset-generation
Generation code for the CLEAR dataset (Compositional Language and Elementary Acoustic Reasoning)