farisalasmary

youtube-dl

Command-line program to download videos from YouTube.com and other video sites

llm-course

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

TTS

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

EasyOCR

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

d2l-en

Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.

mamba

Mamba SSM architecture

surya

OCR, layout analysis, reading order, line detection in 90+ languages

BERTopic

Leveraging BERT and c-TF-IDF to create easily interpretable topics.

facenet-pytorch

Pretrained Pytorch face detection (MTCNN) and facial recognition (InceptionResnet) models

deep-text-recognition-benchmark

Text recognition (optical character recognition) with deep learning methods, ICCV 2019

imagehash

A Python Perceptual Image Hashing Module

vector-quantize-pytorch

Vector (and Scalar) Quantization, in Pytorch

gentle

gentle forced aligner

research-charnet

CharNet: Convolutional Character Networks

CDiffuSE

Conditional Diffusion Probabilistic Model for Speech Enhancement

Dynamic-memory-networks-plus-Pytorch

Implementation of Dynamic memory networks plus in Pytorch

TAO-Amodal

Official Code for Tracking Any Object Amodally

afaligner

📈 A forced aligner intended for synchronization of narrated text

text_search

Some fast-ish algorithms for batch text search in moderate-sized collections, intended for data cleanup

SRFormer-Text-Det

[AAAI 2024] SRFormer: Text Detection Transformer with Incorporated Segmentation and Regression

RoBERTa_Encoder_Decoder_Product_Names

Define Transformers, T5 model and RoBERTa Encoder decoder model for product names generation

end2end

Losses and decoders for end-to-end ASR and OCR

deep-diacritization

Official Repository of the Deep Diacritization Paper

NoRefER

kaldi-align

A basic forced aligner using Kaldi and gruut

stt-align

Aligns a known transcript with speech-to-text output

ABSA-Hotels

Semeval-2016 task 5: Aspect based sentiment analysis. Arabic Dataset for Hotels reviews.

HAAD

Human Annotated Arabic Dataset of Book Reviews for Aspect Based Sentiment Analysis

Modified-Label-Studio

Label-Studio for Data Annotations have been modified. Here It can be used with multi users with safe control over the data. No user can delete labels, predictions or make changes in setting.

ABSA-for-Affective-News-Analysis-

This repository is related to our work on using Aspect-Based Sentiment Analysis (ABSA) for Affective News Analysis