ai-forever / OCR-model
An easy-to-run OCR model pipeline based on CRNN and CTC loss
☆46Updated 2 years ago
Alternatives and similar repositories for OCR-model:
Users that are interested in OCR-model are comparing it to the libraries listed below
- ☆43Updated 2 years ago
- Repository containing our datasets for HTR (handwritten text recognition) task.☆24Updated 2 years ago
- Text reading pipeline that combines segmentation and OCR-models.☆26Updated 2 years ago
- 1st place (public LB) solution of AIJ2020 Sberbank competition (Digital Peter)☆18Updated 4 years ago
- Handwritten Text Generation☆16Updated 2 years ago
- Model for document segmentation trained on the midv-500-models dataset.☆74Updated 4 years ago
- OCR seq2seq resnet+transformer☆67Updated 4 years ago
- Kazakh Offline Handwritten Text Dataset☆15Updated 2 years ago
- The solution and code for NTO AI Olympics 2022.☆19Updated 2 years ago
- An unstructured set of helper functions☆59Updated 3 years ago
- Handwritten Kazakh and Russian (HKR) database for text recognition☆65Updated 3 years ago
- Packaged, Pytorch-based, easy to use, cross-platform version of the CRAFT text detector☆258Updated 2 years ago
- Some augmentations that I hasn't found in other repositories and libraries.☆26Updated last year
- This is the github repository for converting craft pretrained model to tflite version☆33Updated 3 years ago
- Fast and accurate object detection with end-to-end GPU optimization☆25Updated 5 years ago
- PyTorch optimizations and benchmarking☆56Updated 3 years ago
- Distorted Document Images dataset (DDI-100).☆132Updated 2 years ago
- Attention-based sequence-to-sequence model for handwritten word recognition☆56Updated 4 months ago
- Creating multimodal multitask models☆50Updated 2 years ago
- The 2nd place Solution for Digital Peter competition.☆10Updated 3 years ago
- Code and pre-trained models for detecting spoofing attacks from images.☆39Updated 4 years ago
- Official baseline solutions to Yandex Cup ML challenge☆32Updated 3 years ago
- Multiple infras for one machine learning task☆27Updated last year
- RuTransform: python framework for adversarial attacks and text data augmentation for Russian☆18Updated last year
- ☆22Updated 3 years ago
- REST API for sentence tokenization and embedding using Multilingual Universal Sentence Encoder.☆52Updated 3 years ago
- RuCLIP tiny (Russian Contrastive Language–Image Pretraining) is a neural network trained to work with different pairs (images, texts).☆32Updated 2 years ago
- Dataset of clothes for metric learning tasks and not only for this.☆20Updated 5 years ago
- TextTron is a simple light-weight image processing based text detector for document images.☆51Updated 4 years ago
- Easter2.0: IMPROVING CONVOLUTIONAL MODELS FOR HANDWRITTEN TEXT RECOGNITION☆79Updated last year