breezedeus

CnOCR

CnOCR: Awesome Chinese/English OCR Python toolkits based on PyTorch. It comes with 20+ well-trained models for different application scenarios and can be used directly after installation. 【基于 PyTorch/MXNet 的中文/英文 OCR Python 包。】

Pix2Text

Pix In, Latex & Text Out. Recognize Chinese, English Texts, and Math Formulas from Images. 80+ languages are supported.

CnSTD

CnSTD: 基于 PyTorch/MXNet 的 中文/英文 场景文字检测（Scene Text Detection）、数学公式检测（Mathematical Formula Detection, MFD）、篇章分析（Layout Analysis）的Python3 包

cnstd-cnocr-models

pretrained models for cnocr

antiOCR

Anti OCR, Free Texts (拒绝被OCR，让文字得到自由)。把文本转换成机器无法识别但人可读的图片。

LoveShare

breezedeus的各种分享

CnMFD_Dataset

Chinese Mathematical Formula Detection (MFD) Dataset 中文文档数学公式检测数据集

breezedeus.github.io

Breezedeus's Blog

text_renderer_old

Generate text images for training deep learning ocr model

thesis_CF_at_Netflix_Prize

博士论文《Netflix Prize 中的协同过滤算法》以及对应的答辩PPT

Pix2Text-Mac

Pix2Text MacOS App: A Mac Desktop App for Mathematical Formula Recognition and Text Recognition. Mac 本地数学公式识别和文本识别工具

Coin-CLIP

Coin-CLIP: fine-tuned with a vast collection of coin images from CLIP using contrastive learning. It enhances feature extraction for coins, boosting image search accuracy. This model merges Visual Transformer (ViT) with CLIP's multimodal learning, optimized for numismatic applications.

CHINESE-OCR

[python3.6] 运用tf实现自然场景文字检测,keras/pytorch实现ctpn+crnn+ctc实现不定长场景文字OCR识别

yolov7

Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

CS4CS

CS4CS: Cheat Sheets for Cheat Sheets. Collect plenty of Cheat Sheets For AI related

bert

TensorFlow code and pre-trained models for BERT

DeadSimpleSpeechRecognizer

CNN based Minimal model for recognizing word

Dialog_Corpus

用于训练中英文对话系统的语料库 Datasets for Training Chatbot System；小黄鸡等

diffusion-nbs

Getting started with diffusion

diffuzers

a web ui & api for 🤗 diffusers

entmax

The entmax mapping and its loss, a family of sparse softmax alternatives.

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

fastText.py

A Python interface for Facebook fastText

github-slideshow

A robot powered training repository :robot:

LaTeX-OCR

pix2tex: Using a ViT to convert images of equations into LaTeX code.

NotionNext

使用 NextJS + Notion API 实现的，支持多种部署方案的静态博客，无需服务器、零门槛搭建网站，为Notion和所有创作者设计。 (A static blog built with NextJS and Notion API, supporting multiple deployment options. No server required, zero threshold to set up a website. Designed for Notion and all creators.)

OpenNMT-tf

Open Source Neural Machine Translation in TensorFlow

Self-Supervised-Speech-Pretraining-and-Representation-Learning

Official implementation of the S3PRL toolkit: self-supervised pre-training of Mockingjay, TERA, AALBERT, APC, and more to come. With easy-to-use standard downstream evaluation scripts including phone classification, speaker recognition, and ASR. (All in Pytorch)

speech-to-text-wavenet

Speech-to-Text-WaveNet : End-to-end sentence level English speech recognition based on DeepMind's WaveNet and tensorflow

TensorFlow_Tutorials