ai-forever / ScrabbleGAN
Handwritten Text Generation
☆16Updated last year
Related projects: ⓘ
- ☆41Updated last year
- Repository containing our datasets for HTR (handwritten text recognition) task.☆23Updated 2 years ago
- Text reading pipeline that combines segmentation and OCR-models.☆25Updated last year
- An easy-to-run OCR model pipeline based on CRNN and CTC loss☆43Updated last year
- Handwritten Kazakh and Russian (HKR) database for text recognition☆58Updated 3 years ago
- CLIP implementation for Russian language☆136Updated 10 months ago
- Framework for processing and filtering datasets☆25Updated last month
- Bunch of notebooks for pre-training custom Saiga-like LLM☆13Updated 7 months ago
- RuCLIP tiny (Russian Contrastive Language–Image Pretraining) is a neural network trained to work with different pairs (images, texts).☆32Updated 2 years ago
- 1st place (public LB) solution of AIJ2020 Sberbank competition (Digital Peter)☆18Updated 3 years ago
- Handwritten Text Generation☆19Updated 3 years ago
- ☆15Updated 3 years ago
- ☆69Updated last year
- The solution and code for NTO AI Olympics 2022.☆18Updated 2 years ago
- ☆18Updated 2 years ago
- A list of initiatives for adding new languages to opensource machine translation models☆13Updated this week
- MERA (Multimodal Evaluation for Russian-language Architectures) is a new open benchmark for the Russian language for evaluating fundament…☆57Updated this week
- ☆21Updated 11 months ago
- ☆58Updated 7 months ago
- Распознавание рукописного текста в школьных тетрадях☆14Updated last year
- SAGE: Spelling correction, corruption and evaluation for multiple languages☆129Updated last month
- EasyPortrait - Face Parsing and Portrait Segmentation Dataset☆28Updated 2 weeks ago
- Dalle2-Decoder for image generation tasks☆20Updated 2 years ago
- An easy-to-run semantic segmentation model based on Unet☆13Updated last year
- RuLeanALBERT is a pretrained masked language model for the Russian language that uses a memory-efficient architecture.☆90Updated last year
- RuTransform: python framework for adversarial attacks and text data augmentation for Russian☆17Updated last year
- Augmentex — a library for augmenting texts with errors☆48Updated 2 months ago
- The 2nd place Solution for Digital Peter competition.☆10Updated 2 years ago
- Multiple infras for one machine learning task☆26Updated last year
- RuCLIP-SB (Russian Contrastive Language–Image Pretraining SWIN-BERT) is a multimodal model for obtaining images and text similarities and…☆11Updated 2 years ago