Dulu
Dulu is a small python library for doing OCR on image. Under the hood it uses florence model from microsoft, which is a state of the art vision model for many downstream tasks including OCR.
Installation
pip install dulu
Example Code
Here is a snippet of the code used in the notebook:
from dulu import OCR
from PIL import Image
# Load the image
image = Image.open("./sample_image.png")
image
# Initialize the OCR object
ocr = OCR()
# Recognize text without bounding boxes
text = ocr.recognize_text("./sample_image.png", bbox=False)
print(text)
# Recognize text with bounding boxes
text_with_bbox = ocr.recognize_text("./sample_image.png")
print(text_with_bbox)
List of models
| Model Id | Model size | Model Description |
|---|---|---|
| Florence-2-base | 0.23B | Pretrained model with FLD-5B |
| Florence-2-large | 0.77B | Pretrained model with FLD-5B |
| Florence-2-base-ft | 0.23B | Finetuned model on a collection of downstream tasks |
| Florence-2-large-ft | 0.77B | Finetuned model on a collection of downstream tasks |
By default we use Florence-2-base-ft model, you can over ride this with any other above in the list when
instantiating OCR(model_name="microsoft/{model_id})
Acknowledgments
1 maintainer
Metadata
1 maintainer
Release files for dulu 0.1.4
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| dulu-0.1.4.tar.gz | 292.2 kB | Without provenance | Details for dulu-0.1.4.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| dulu-0.1.4-py3-none-any.whl | Python 3 | none | any | Details for dulu-0.1.4-py3-none-any.whl |
Total release size: 300.0 kB
Release files / dulu-0.1.4.tar.gz
| Download URL | dulu-0.1.4.tar.gz |
|---|---|
| Size | 292.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
5ab9289c32d19088b312cb3adf2dfb8a065fd5dedce80451290df99c13aa8dcc
|
|
BLAKE2b-256 checksum How to use checksums |
78d699a06f4403468ba9901028f5389ff7805cabead150053937e972aeed2e7b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/5.1.1 CPython/3.12.7
|
Release files / dulu-0.1.4-py3-none-any.whl
| Download URL | dulu-0.1.4-py3-none-any.whl |
|---|---|
| Size | 7.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
4e81e6783bec204320cbe9be5bc344683b0394cc79dc3890fd28a155f413c7f2
|
|
BLAKE2b-256 checksum How to use checksums |
ab5e0aff1aae96ad8b4c2d9c18948a378808c671a6c301afcf5dd923d7c3f138
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/5.1.1 CPython/3.12.7
|
Security for dulu 0.1.4
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
