There are 4 repositories under ctc-loss topic.
验证码识别
Convolutional Recurrent Neural Networks(CRNN) for Scene Text Recognition
Pytorch Implementation For LPRNet, A High Performance And Lightweight License Plate Recognition Framework.
Connectionist Temporal Classification (CTC) decoding algorithms: best path, beam search, lexicon search, prefix search, and token passing. Implemented in Python.
百度云魅族深度学习应用大赛
Pytorch implementation of CRNN (CNN + RNN + CTCLoss) for all language OCR.
Use Convolutional Recurrent Neural Network to recognize the Handwritten line text image without pre segmentation into words or characters. Use CTC loss Function to train.
Lightweight CRNN for OCR (including handwritten text) with depthwise separable convolutions and spatial transformer module [keras+tf]
Application of Connectionist Temporal Classification (CTC) for Speech Recognition (Tensorflow 1.0 but compatible with 2.0).
A fully convolution-network for speech-to-text, built on pytorch.
VietASR - Vietnamese Automatic Speech Recognition
Speech Recognition model based off of FAIR research paper built using Pytorch.
Handwritten Kazakh and Russian (HKR) database for text recognition
This repo contains code written by MXNet for ocr tasks, which uses an cnn-lstm-ctc architecture to do text recognition.
An implementation of RNN-Transducer loss in TF-2.0.
A deep learning model (DCNNs+Bi LSTMs+CTC Loss) for identification of Handwritten Arabic Text
Implemented a car plate recognition algorithm based on CTC loss
End-to-end captcha image recognition using PyTorch and CTC loss binding.
A tutorial on how to work around ‘Mutating arrays is not supported’ error while performing automatic differentiation (AD) using the Julia package Zygote.
RNN CTC by using TensorFlow.
A TensorFlow implementation of hybird CNN-LSTM model with CTC loss for OCR problem
Optical character recognition Using Deep Learning
Pytorch project accompanying the paper "Training Deep Pitch-Class Representations With a Multi-Label CTC Loss", ISMIR 2021.
Focal CTC for End-To-End OMR task with Class Imbalance, SangCTC (Part I)
Enables computing the gradient of the parameters of Hidden Markov Models (HMMs)
Train a Text Recognition CRNN model with Tensorflow2 & Keras & IAM Dataset. Convolutional Recurrent Neural Network. CTC.