dazzle-me

whisper

Robust Speech Recognition via Large-Scale Weak Supervision

xgboost

Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C++ and more. Runs on single machine, Hadoop, Spark, Dask, Flink and DataFlow

nlp_course

YSDA course in Natural Language Processing

einops

Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)

mmsegmentation

OpenMMLab Semantic Segmentation Toolbox and Benchmark.

Awesome-Diffusion-Models

A collection of resources and papers on Diffusion Models

wenet

Production First and Production Ready End-to-End Speech Recognition Toolkit

deep-rl-class

This repo contains the syllabus of the Hugging Face Deep Reinforcement Learning Course.

CelebAMask-HQ

A large-scale face dataset for face parsing, recognition, generation and editing.

arcface-pytorch

TransformerEngine

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilization in both training and inference.

EfficientFormer

EfficientFormerV2 [ICCV 2023] & EfficientFormer [NeurIPs 2022]

conformer

[Unofficial] PyTorch implementation of "Conformer: Convolution-augmented Transformer for Speech Recognition" (INTERSPEECH 2020)

swin2sr

[ECCV] Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration. Advances in Image Manipulation (AIM) workshop ECCV 2022. Try it out! over 3.3M runs https://replicate.com/mv-lab/swin2sr

dla

Deep learning for audio processing

pytorch_misc

Code snippets created for the PyTorch discussion board

Awesome-Mixture-of-Experts-Papers

A curated reading list of research in Mixture-of-Experts(MoE).

ema-pytorch

A simple way to keep track of an Exponential Moving Average (EMA) version of your pytorch model

Enjoy-Hamburger

[ICLR 2021 top 3%] Is Attention Better Than Matrix Decomposition?

video2numpy

Optimized library for large-scale extraction of frames and audio from video.

protein-bert-pytorch

Implementation of ProteinBERT in Pytorch

Cross-iterationBatchNorm

kaggle-sartorius-cell-instance-segmentation-solution

Solution of Kaggle competition: Sartorius - Cell Instance Segmentation

Rotated-Rectangle-Crop-OpenCV

Rotated Rectangle Crop Function for OpenCV

dicomsdl

DICOM Software Development Library

clshub

nvjpeg2k-python

NVJPEG2K python binding

mch-hackathon

Moscow City Hack fake news detection case solution

yandex-cup-2022-ML-Audio-3rd

telegram-data-analyzer

This repo is a command line node script that reads telegram's exported data and outputs interesting aggregate data as json and a more simplified text chat.