rasoolims

minLoRA

minLoRA: a minimal PyTorch library that allows you to apply LoRA to any PyTorch model.

torch_cif

A fast parallel PyTorch implementation of the "CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition" https://arxiv.org/abs/1905.11235.

infinibatch

Efficient, check-pointed data loading for deep learning with massive data sets.

raspy

An interactive exploration of Transformer programming.

performer-pytorch

An implementation of Performer, a linear attention-based transformer, in Pytorch

whisper

Robust Speech Recognition via Large-Scale Weak Supervision

espnet

End-to-End Speech Processing Toolkit

Deep-Learning-in-Production

In this repository, I will share some useful notes and references about deploying deep learning-based models in production.

pytorchforaudio

Code for the "PyTorch for Audio + Music Processing" series on The Sound of AI YouTube channel.

ImageTranslate

"Wikily" Neural Machine Translation Tailored to Cross-Lingual Tasks.

bolt

10x faster matrix and vector operations

accelerate

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

wit

WIT (Wikipedia-based Image Text) Dataset is a large multimodal multilingual dataset comprising 37M+ image-text sets with 11M+ unique images across 100+ languages.

parsinlu

A comprehensive suite of high-level NLP tasks for Persian language

LwLLDatasetAPI

korean-parallel-corpora

Korean Parallel Corpus

pdf2pptx

Convert your (Beamer) PDF slides to (Powerpoint) PPTX

persian-raw-text

Persian raw text - حدود ۸۰ گیگابایت متن خام فارسی

MASS

MASS: Masked Sequence to Sequence Pre-training for Language Generation

ImageCaptioning.pytorch

I decide to sync up this repo and self-critical.pytorch. (The old master is in old master branch for archive)

pytorch-lightning

Pretrain, finetune and deploy AI models on multiple GPUs, TPUs with zero code changes.

NCRFpp

NCRF++, a Neural Sequence Labeling Toolkit. Easy use to any sequence labeling tasks (e.g. NER, POS, Segmentation). It includes character LSTM/CNN, word LSTM/CNN and softmax/CRF components.

PyTorch-NLP

Basic Utilities for PyTorch Natural Language Processing (NLP)

Mask-Predict

A masked language modeling objective to train a model to predict any subset of the target words, conditioned on both the input text and a partially masked target translation.

Text-to-Image-Synthesis

Pytorch implementation of Generative Adversarial Text-to-Image Synthesis paper

detectron2

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

UD_Persian-PerDT

Universal Persian Dependency Treebank (UPerDT) is the result of automatic coversion of Persian Dependency Treebank (PerDT) with extensive manual corrections.

multilingual-google-image-scraper

simple python3 module for scraping google images across many languages, based on input dictionaries

mmf

A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)

bprForBli

Implementation of Bayesian Personalized Ranking for Bilingual Lexicon Induction