GitHub topics: ctc-loss

Repositories

ypwhs/captcha_break

验证码识别

Language: Jupyter Notebook - Size: 6.6 MB - Last synced at: 1 day ago - Pushed at: about 3 years ago - Stars: 2,766 - Forks: 680

giladodinak/mlinc

Machine Learning from scratch in C

Language: C - Size: 5.55 MB - Last synced at: 10 days ago - Pushed at: 11 days ago - Stars: 1 - Forks: 1

parlance/ctcdecode

PyTorch CTC Decoder bindings

Language: C++ - Size: 753 KB - Last synced at: 13 days ago - Pushed at: about 1 year ago - Stars: 835 - Forks: 251

zjykzj/crnn-ctc

CRNN/LPRNet/STNet + CTC + CCPD

Language: Python - Size: 11.5 MB - Last synced at: 20 days ago - Pushed at: 20 days ago - Stars: 10 - Forks: 4

srvk/eesen

The official repository of the Eesen project

Language: C++ - Size: 5.86 MB - Last synced at: 14 days ago - Pushed at: almost 6 years ago - Stars: 829 - Forks: 342

kkinzzza/MorseRecognition

This project is dedicated to Morse code recognition on different audio signals. It includes analytical and ML methods for signal processing and tone morse signals decoding.

Language: Jupyter Notebook - Size: 4.28 MB - Last synced at: 23 days ago - Pushed at: 23 days ago - Stars: 0 - Forks: 0

ysig/learnable-typewriter

The Learnable Typewriter: A Generative Approach to Text Line Analysis

Language: Python - Size: 374 KB - Last synced at: 19 days ago - Pushed at: 7 months ago - Stars: 33 - Forks: 1

18520339/tf2-sequence-recognition-toolkit

TensorFlow 2 Toolkit for Sequence-level Text Recognition that simplifies the process of importing, handling, and visualizing sequence data, as well as providing most used loss functions and evaluation metrics in the development of Sequence Text Recognition models

Language: Python - Size: 3.99 MB - Last synced at: 7 days ago - Pushed at: 11 months ago - Stars: 2 - Forks: 0

sushant097/Handwritten-Line-Text-Recognition-using-Deep-Learning-with-Tensorflow

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.

Language: Python - Size: 2.19 MB - Last synced at: about 1 month ago - Pushed at: 5 months ago - Stars: 307 - Forks: 125

vietai/ASR

End-to-End Vietnamese Speech Recognition using wav2vec 2.0

Size: 10.7 KB - Last synced at: about 1 month ago - Pushed at: over 3 years ago - Stars: 98 - Forks: 9

Holmeyoung/crnn-pytorch

Pytorch implementation of CRNN (CNN + RNN + CTCLoss) for all language OCR.

Language: Python - Size: 43.9 KB - Last synced at: about 1 month ago - Pushed at: over 5 years ago - Stars: 384 - Forks: 103

harshuljain13/OCR

Optical character recognition Using Deep Learning

Language: Jupyter Notebook - Size: 7.5 MB - Last synced at: about 1 month ago - Pushed at: almost 7 years ago - Stars: 30 - Forks: 7

githubharald/CTCDecoder

Connectionist Temporal Classification (CTC) decoding algorithms: best path, beam search, lexicon search, prefix search, and token passing. Implemented in Python.

Language: Python - Size: 1010 KB - Last synced at: about 1 month ago - Pushed at: almost 4 years ago - Stars: 825 - Forks: 183

sirius-ai/LPRNet_Pytorch

Pytorch Implementation For LPRNet, A High Performance And Lightweight License Plate Recognition Framework.

Language: Python - Size: 19.6 MB - Last synced at: about 2 months ago - Pushed at: almost 2 years ago - Stars: 979 - Forks: 246

Ad882/Recurrent-Neural-Network-Acoustic-Models-for-Speech-Recognition

Recurrent Neural Network Acoustic Models for Speech Recognition

Language: Jupyter Notebook - Size: 78.8 MB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 0 - Forks: 0

Alan-6666/chinese_asr

a demo of chinese asr

Language: Python - Size: 149 KB - Last synced at: 14 days ago - Pushed at: over 3 years ago - Stars: 4 - Forks: 2

alexeytochin/tf_seq2seq_losses

TensorFlow implementations of losses for sequence to sequence machine learning models

Language: Python - Size: 73.2 KB - Last synced at: about 1 month ago - Pushed at: 11 months ago - Stars: 10 - Forks: 2

jpuigcerver/pytorch-baidu-ctc

PyTorch bindinga for Baidu's Warp-CTC

Language: Shell - Size: 43.9 KB - Last synced at: 2 days ago - Pushed at: almost 6 years ago - Stars: 60 - Forks: 11

toanlcgift/captcha-ocr-mlnet

Implementation Captcha OCR using CNNs, RNNs and CTC loss, using ML.Net, ONNX runtime

Language: C# - Size: 1.57 MB - Last synced at: 2 months ago - Pushed at: 4 months ago - Stars: 0 - Forks: 0

gasparian/CRNN-OCR-lite

Lightweight CRNN for OCR (including handwritten text) with depthwise separable convolutions and spatial transformer module [keras+tf]

Language: Python - Size: 136 MB - Last synced at: 25 days ago - Pushed at: almost 6 years ago - Stars: 148 - Forks: 29

ugnelis/tensorflow-rnn-ctc 📦

RNN CTC by using TensorFlow.

Language: Python - Size: 746 KB - Last synced at: 6 days ago - Pushed at: about 6 years ago - Stars: 30 - Forks: 14

christofw/pitchclass_mctc

Pytorch project accompanying the paper "Training Deep Pitch-Class Representations With a Multi-Label CTC Loss", ISMIR 2021.

Language: HTML - Size: 346 MB - Last synced at: 2 months ago - Pushed at: about 3 years ago - Stars: 25 - Forks: 3

manishdhakal/ASR-Nepali-using-CNN-BiLSTM-ResNet

Automatic speech recognition for the Nepali language using CNN, bidirectional LSTM and ResNet - IEEE (ICICT - 2022)

Language: Python - Size: 9.98 MB - Last synced at: 6 months ago - Pushed at: 6 months ago - Stars: 16 - Forks: 9

harshvardhansgupta/OCR_Model

Our AI model is designed to predict text from images of handwritten words. It combines Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) for enhanced accuracy. Trained on the IAM Handwriting Word Database from Kaggle, the model achieves a character-level accuracy of 89.4124% and a word-level accuracy of 70.8018%

Language: Jupyter Notebook - Size: 1.15 GB - Last synced at: 7 months ago - Pushed at: 7 months ago - Stars: 0 - Forks: 0

ypwhs/baiduyun_deeplearning_competition

百度云魅族深度学习应用大赛

Language: Jupyter Notebook - Size: 10.8 MB - Last synced at: about 1 month ago - Pushed at: about 3 years ago - Stars: 422 - Forks: 179

dangvansam/viet-asr

VietASR - Vietnamese Automatic Speech Recognition

Language: Python - Size: 289 MB - Last synced at: 7 months ago - Pushed at: 7 months ago - Stars: 102 - Forks: 46

madeyoga/Handwritten-Text-Recognition

Train a Text Recognition CRNN model with Tensorflow2 & Keras & IAM Dataset. Convolutional Recurrent Neural Network. CTC.

Language: Jupyter Notebook - Size: 2.19 MB - Last synced at: about 1 month ago - Pushed at: about 5 years ago - Stars: 20 - Forks: 5

Kirili4ik/QuartzNet-ASR-pytorch

Automatic Speech Recognition (ASR) model QuartzNet trained on English CommonVoice. In PyTroch with CTC loss and beam search.

Language: Jupyter Notebook - Size: 1.2 MB - Last synced at: about 15 hours ago - Pushed at: over 4 years ago - Stars: 16 - Forks: 3

X-rayLaser/keras-cnn-1drnn-ctc

A toolkit for training CNN-1DRNN-CTC model to perform line-level Handwritten Text Recognition

Language: Python - Size: 146 KB - Last synced at: about 18 hours ago - Pushed at: about 5 years ago - Stars: 9 - Forks: 1

Ankurac7/LipNet

A deep learning model which is able to perform lip reading!

Language: Jupyter Notebook - Size: 484 MB - Last synced at: 9 months ago - Pushed at: 9 months ago - Stars: 0 - Forks: 0

zaanind/Asr_CTC

This repository provides a Jupyter notebook for (CTC) based Automatic Speech Recognition (ASR) system using TensorFlow and Keras. The primary focus of this repository is to demonstrate the implementation of a CTC ASR model and to show how to train it effectively on the "Yes No" dataset.

Language: Jupyter Notebook - Size: 1.23 MB - Last synced at: 9 months ago - Pushed at: 9 months ago - Stars: 2 - Forks: 0

philipperemy/tensorflow-ctc-speech-recognition

Application of Connectionist Temporal Classification (CTC) for Speech Recognition (Tensorflow 1.0 but compatible with 2.0).

Language: Python - Size: 634 KB - Last synced at: 14 days ago - Pushed at: about 4 years ago - Stars: 130 - Forks: 46

idiap/HMMGradients.jl

Enables computing the gradient of the parameters of Hidden Markov Models (HMMs)

Language: Julia - Size: 256 KB - Last synced at: about 1 month ago - Pushed at: almost 4 years ago - Stars: 22 - Forks: 0

TienNHM/CRNN-OCR

OCR using CRNN (CNN - Deep Bidirectional LSTM) and CTC loss

Language: Python - Size: 279 MB - Last synced at: about 2 months ago - Pushed at: about 4 years ago - Stars: 1 - Forks: 0

agSwift/whiteboard-captioning

An approach to handwriting recognition using individual Bézier curves.

Language: Jupyter Notebook - Size: 772 MB - Last synced at: 5 months ago - Pushed at: almost 2 years ago - Stars: 3 - Forks: 0

HansRen1024/CTCDecoder

ctc decoder

Language: Python - Size: 1000 Bytes - Last synced at: about 1 year ago - Pushed at: about 5 years ago - Stars: 1 - Forks: 0

tetrapod0/7-Segment-Digit-OCR

Red 7 segment digit OCR.

Language: Jupyter Notebook - Size: 12.3 MB - Last synced at: about 1 year ago - Pushed at: over 2 years ago - Stars: 0 - Forks: 1

tetrapod0/captcha_OCR

CTC loss 기반 captcha 이미지 OCR

Language: Jupyter Notebook - Size: 212 KB - Last synced at: about 1 year ago - Pushed at: over 3 years ago - Stars: 0 - Forks: 0

tetrapod0/Number-OCR

Number OCR

Language: Jupyter Notebook - Size: 12.4 MB - Last synced at: about 1 year ago - Pushed at: over 2 years ago - Stars: 0 - Forks: 0

LaurentVeyssier/Automatic-Speech-Recognizer

Build end-to-end Deep Neural Network to translate speech to text (ASR model)

Language: Jupyter Notebook - Size: 10.7 MB - Last synced at: about 1 year ago - Pushed at: over 4 years ago - Stars: 3 - Forks: 0

tranbahien/CTC-OCR

A TensorFlow implementation of hybird CNN-LSTM model with CTC loss for OCR problem

Language: Python - Size: 80.1 KB - Last synced at: 12 months ago - Pushed at: about 6 years ago - Stars: 28 - Forks: 8

sir-timio/HTR 📦

Handwritten text recognition

Language: Jupyter Notebook - Size: 61.6 MB - Last synced at: about 1 year ago - Pushed at: almost 3 years ago - Stars: 19 - Forks: 4

orbant12/Automatic_Speech_Recognition---Tensorflow

Speech --> Text - 🧠Recurrent Neural Network

Language: Jupyter Notebook - Size: 536 KB - Last synced at: about 1 year ago - Pushed at: about 1 year ago - Stars: 0 - Forks: 0

christofw/multipitch_mctc

Pytorch project accompanying the paper "Learning Multi-Pitch Estimation From Weakly Aligned Score-Audio Pairs Using a Multi-Label CTC Loss", IEEE WASPAA 2021.

Language: HTML - Size: 277 MB - Last synced at: over 1 year ago - Pushed at: over 3 years ago - Stars: 5 - Forks: 1

rakeshvar/rnn_ctc

Recurrent Neural Network and Long Short Term Memory (LSTM) with Connectionist Temporal Classification implemented in Theano. Includes a Toy training example.

Language: Python - Size: 604 KB - Last synced at: 6 months ago - Pushed at: almost 9 years ago - Stars: 220 - Forks: 80

dbrcina/MSc-Thesis-FER-2021-22

MSc Thesis at FER-2021/22 led by izv. prof. dr. sc. Marko Čupić

Language: Jupyter Notebook - Size: 144 MB - Last synced at: over 1 year ago - Pushed at: almost 3 years ago - Stars: 1 - Forks: 0

xmfbit/warpctc-caffe

Combine Baidu Research warpctc with Caffe

Language: C++ - Size: 37.9 MB - Last synced at: over 1 year ago - Pushed at: over 3 years ago - Stars: 96 - Forks: 61

rajesh-bhat/spark-ai-summit-2020-text-extraction

Language: Jupyter Notebook - Size: 105 MB - Last synced at: about 1 year ago - Pushed at: over 4 years ago - Stars: 58 - Forks: 33

xmfbit/captcha-recognition

End-to-end captcha image recognition using PyTorch and CTC loss binding.

Language: Python - Size: 412 KB - Last synced at: over 1 year ago - Pushed at: over 7 years ago - Stars: 32 - Forks: 13

type-a/speechnet

Automatic Speech Recognition

Language: Python - Size: 89.8 KB - Last synced at: about 1 year ago - Pushed at: over 6 years ago - Stars: 20 - Forks: 2

MaybeShewill-CV/CRNN_Tensorflow

Convolutional Recurrent Neural Networks(CRNN) for Scene Text Recognition

Language: Python - Size: 544 MB - Last synced at: over 1 year ago - Pushed at: about 2 years ago - Stars: 1,027 - Forks: 392

nemoramo/acoustic_model

This is a sub-repository in building to create acoustic model in Mandarin speech recognition.

Language: Python - Size: 11.3 MB - Last synced at: over 1 year ago - Pushed at: over 5 years ago - Stars: 6 - Forks: 8

akashbangera758/CRNN_Text_Recognition_Tensorflow

This is a Tensorflow implementation of text recognition model from the paper "An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition".

Language: Python - Size: 23.4 KB - Last synced at: over 1 year ago - Pushed at: almost 6 years ago - Stars: 0 - Forks: 0

silversparro/wav2letter.pytorch

A fully convolution-network for speech-to-text, built on pytorch.

Language: Python - Size: 105 KB - Last synced at: over 1 year ago - Pushed at: almost 5 years ago - Stars: 123 - Forks: 23

theAB316/captcha_rec

Captcha Recognition in PyTorch

Language: Jupyter Notebook - Size: 18.1 MB - Last synced at: over 1 year ago - Pushed at: almost 5 years ago - Stars: 0 - Forks: 0

Viddesh1/HTE

Implementation of the TCS ION Remote Internship RIO-125

Language: Jupyter Notebook - Size: 90 MB - Last synced at: 3 months ago - Pushed at: over 1 year ago - Stars: 0 - Forks: 0

mskelb/OCR_SB

Size: 421 MB - Last synced at: over 1 year ago - Pushed at: over 1 year ago - Stars: 1 - Forks: 0

jimitshah77/Focal-CTC-OMR

Focal CTC for End-To-End OMR task with Class Imbalance, SangCTC (Part I)

Language: Jupyter Notebook - Size: 2.28 MB - Last synced at: about 1 month ago - Pushed at: almost 5 years ago - Stars: 22 - Forks: 8

georgeretsi/HTR-ctc

Pytorch implementation of HTR on IAM dataset (word or line level + CTC loss)

Language: Python - Size: 11.2 MB - Last synced at: almost 2 years ago - Pushed at: almost 3 years ago - Stars: 16 - Forks: 7

gawy/aind2-asr-speech-recognition

ASR with Deep Neural Networks

Language: Jupyter Notebook - Size: 16.6 MB - Last synced at: almost 2 years ago - Pushed at: about 5 years ago - Stars: 0 - Forks: 0

William1617/ctc_kws

Language: Python - Size: 54.7 KB - Last synced at: almost 2 years ago - Pushed at: almost 2 years ago - Stars: 1 - Forks: 1

kolloldas/tf-transliteration

TensorFlow implementation of Google i18n Transliteration Model

Language: Python - Size: 10.7 KB - Last synced at: 8 months ago - Pushed at: about 7 years ago - Stars: 7 - Forks: 6

agarwaltanmay/stanford-ctc Fork of amaas/stanford-ctc

Neural net code for lexicon-free speech recognition with connectionist temporal classification

Language: Python - Size: 263 KB - Last synced at: about 2 years ago - Pushed at: about 9 years ago - Stars: 0 - Forks: 0

mikita95/asr-e2e

Automatic speech recognition system using end-to-end approach for Russian speech

Language: Python - Size: 26.8 MB - Last synced at: 7 months ago - Pushed at: over 7 years ago - Stars: 1 - Forks: 0

to-schi/ASR-Deepspeech2-Tensorflow

An end-to-end speech recognition engine similar to DeepSpeech2

Language: Jupyter Notebook - Size: 2.19 MB - Last synced at: over 1 year ago - Pushed at: over 2 years ago - Stars: 2 - Forks: 0

Anna868/Arabic-Handwritten-OCR

A deep learning model (DCNNs+Bi LSTMs+CTC Loss) for identification of Handwritten Arabic Text

Language: Jupyter Notebook - Size: 4.28 MB - Last synced at: about 2 years ago - Pushed at: almost 3 years ago - Stars: 12 - Forks: 3

iamjanvijay/rnnt

An implementation of RNN-Transducer loss in TF-2.0.

Language: Python - Size: 140 MB - Last synced at: 3 months ago - Pushed at: about 2 years ago - Stars: 45 - Forks: 9

abdoelsayed2016/HKR_Dataset

Handwritten Kazakh and Russian (HKR) database for text recognition

Size: 5.78 MB - Last synced at: about 2 years ago - Pushed at: over 3 years ago - Stars: 40 - Forks: 3

chenmingxiang110/Car-Plate-Recognition

Implemented a car plate recognition algorithm based on CTC loss

Language: Jupyter Notebook - Size: 1.01 MB - Last synced at: about 2 years ago - Pushed at: almost 4 years ago - Stars: 32 - Forks: 8

lordtt13/automatic-speech-recognition

A few projects pertaining to the creation of ASR Models using ctc loss and simple softmax loss to classify small datasets

Language: Jupyter Notebook - Size: 1.09 MB - Last synced at: about 2 years ago - Pushed at: over 2 years ago - Stars: 2 - Forks: 1

emcdona1/crnn_models_single_gpu

Tuning, training, and transfer learning CRNN models for handwritten text words.

Language: Jupyter Notebook - Size: 72.1 MB - Last synced at: about 2 years ago - Pushed at: over 2 years ago - Stars: 1 - Forks: 0

mohammadhashemii/FFC-RNN

PyTorch Implementation of Fast Fourier Convolution-RNN with CTC loss for Handwritten Recognition

Language: Python - Size: 1.67 MB - Last synced at: about 2 years ago - Pushed at: over 2 years ago - Stars: 2 - Forks: 1

pmuilu/ocr_crnn

PyTorch CNN+LSTM model for OCR

Language: Python - Size: 7.81 KB - Last synced at: about 2 years ago - Pushed at: about 5 years ago - Stars: 3 - Forks: 2

rjnp2/Text-Recognition-using-Deep-Learning

Language: Jupyter Notebook - Size: 759 KB - Last synced at: almost 2 years ago - Pushed at: over 4 years ago - Stars: 3 - Forks: 1

harangp/tfjsctcloss

CTC loss and gradient implementation for Tensorflow.JS

Language: TypeScript - Size: 789 KB - Last synced at: over 1 year ago - Pushed at: over 2 years ago - Stars: 5 - Forks: 0

lvliguoren/crnn-pytorch

Image-based Sequence Recognition(CRNN)

Language: Python - Size: 9.72 MB - Last synced at: almost 2 years ago - Pushed at: almost 5 years ago - Stars: 1 - Forks: 0

nicozorza/speech-to-text

Sistema conversor de habla a texto basado en redes neuronales

Language: Python - Size: 79.4 MB - Last synced at: about 2 years ago - Pushed at: over 2 years ago - Stars: 2 - Forks: 0

LearnedVector/Wav2Letter

Speech Recognition model based off of FAIR research paper built using Pytorch.

Language: Python - Size: 186 KB - Last synced at: about 2 years ago - Pushed at: over 6 years ago - Stars: 81 - Forks: 24

Anusha-Manjunath-03/Handwritten-Text-Recognition

IAM Database: https://fki.tic.heia-fr.ch/databases/download-the-iam-handwriting-database

Language: Jupyter Notebook - Size: 16.2 MB - Last synced at: about 2 years ago - Pushed at: over 2 years ago - Stars: 0 - Forks: 0

ChuhanZhou/Scene_Text_Recognition

A text recognition model based on CNN and CTCloss.

Language: Python - Size: 3.13 MB - Last synced at: about 2 years ago - Pushed at: over 2 years ago - Stars: 0 - Forks: 0

01-vyom/End_2_End_Automatic_Speech_Recognition_For_Gujarati

[ICON 2020] TensorFlow Code for "End-to-End Automatic Speech Recognition System for Gujarati"

Language: Python - Size: 28.9 MB - Last synced at: about 2 years ago - Pushed at: almost 4 years ago - Stars: 7 - Forks: 4

xieliang555/Automatic-Speech-Recognition

End-to-end ASR system on TIMIT

Language: Python - Size: 64.5 KB - Last synced at: about 2 years ago - Pushed at: almost 5 years ago - Stars: 9 - Forks: 1

HristovB/Speech_Recognition_Macedonian

Speech recognition model for recognising Macedonian spoken language.

Language: Python - Size: 52.6 MB - Last synced at: about 2 years ago - Pushed at: over 3 years ago - Stars: 5 - Forks: 3

mrzaizai2k/Multi-handwritten-digit-recognition-CRNN-CTC-loss-

I have trained a simple model with CRNN + CTC loss for multi handwritten digit recognition.

Language: Jupyter Notebook - Size: 274 KB - Last synced at: almost 2 years ago - Pushed at: over 2 years ago - Stars: 2 - Forks: 1

ss87021456/mfcc_ctc_speech

apply mfcc feature of waveform with the LSTM + CTC loss architecture

Language: Python - Size: 5.78 MB - Last synced at: about 2 years ago - Pushed at: over 7 years ago - Stars: 5 - Forks: 1

Shakib-IO/Reading_CAPTCHAS

This dataset contains CAPTCHA (Completely Automated Public Turing test to tell Computers and Humans Apart) images. Built in 1997 as a way for users to identify and block bots (in order to prevent spam, DDOS, etc.). They have since then been replaced by reCAPTCHA because they are breakable using Artificial Intelligence (as I encourage you to do). Kaggle: https://www.kaggle.com/fournierp/captcha-version-2-images

Language: Jupyter Notebook - Size: 247 KB - Last synced at: about 2 years ago - Pushed at: over 3 years ago - Stars: 1 - Forks: 0