Image-to-Text
docTR
PyTorch
optical-character-recognition
text-recognition
scene-text-recognition
parseq
vision-transformer
Instructions to use rrainn/doctr-parseq with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- docTR
How to use rrainn/doctr-parseq with docTR:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
| rrainn docTR PARSeq Checkpoint Mirror | |
| This distribution contains an unmodified pretrained model checkpoint from | |
| docTR. The original work is Copyright 2022 Mindee and is distributed under | |
| the Apache License, Version 2.0. See LICENSE for the complete license terms. | |
| Original project: https://github.com/mindee/doctr | |
| Original artifact: parseq-56125471.pt | |
| Original source: https://doctr-static.mindee.com/models?id=v0.7.0/parseq-56125471.pt&src=0 | |
| The rrainn organization maintains this byte-for-byte mirror for reproducible | |
| model resolution. rrainn did not train or modify the model, and this mirror | |
| is not an endorsement by or affiliation with Mindee or the docTR maintainers. | |