OCRmyPDF EasyOCR
This is a plugin to run OCRmyPDF with the EasyOCR engine instead of Tesseract OCR, the default OCR engine for OCRmyPDF. Since EasyOCR is based on PyTorch, it makes use of Nvidia GPUs. Hopefully it will be more performant and accurate than Tesseract OCR.
It is currently experimental and does not implement all of the features of OCRmyPDF with Tesseract, and still relies on Tesseract for certain operations.
Requirements
- OCRmyPDF 17 or newer. As of 0.3.0, this plugin returns structured OCR
results to OCRmyPDF, which renders the text layer itself using its built-in
renderer. (For OCRmyPDF 14–16, use a
< 0.3.0release of this plugin.) - Python 3.11 or newer.
Installation
To use this plugin, first install PyTorch according to the official instructions, which may differ for your platform.
Then install OCRmyPDF-EasyOCR into the same virtual environment or conda environment as you installed PyTorch:
pip install git+https://github.com/ocrmypdf/OCRmyPDF-EasyOCR.git
Once installed, the plugin is discovered automatically through its entry point,
and OCRmyPDF uses EasyOCR for OCR by default (i.e. for --ocr-engine auto). You
can also select it explicitly with --ocr-engine easyocr, or fall back to the
built-in engines with --ocr-engine tesseract / --ocr-engine none. OCR still
depends on Tesseract for some non-OCR tasks (see below).
Development
This project uses uv for package management.
uv sync --group test # create the virtual environment and install dependencies
uv run pytest # run the test suite
The tests need poppler's pdftotext and a Tesseract installation available on
PATH, and will download EasyOCR's models on first run.
Troubleshooting
If you see a log message
Neither CUDA nor MPS are available - defaulting to CPU. Note: This module is much faster with a GPU
then PyTorch is not installed with GPU support.
Pass --easyocr-no-gpu to force CPU mode, or --easyocr-batch-size to tune the
EasyOCR batch size.
To do
Contributions, especially pull requests, are quite welcome!
This plugin is experimental and is missing some features:
- Tesseract is still required to determine page orientation.
- EasyOCR is effectively single-threaded, to eliminate race conditions; OCRmyPDF still parallelizes other stages of the pipeline across pages.
1 maintainer
Metadata
1 maintainer
Release files for ocrmypdf-easyocr 0.3.0
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 |
|---|---|---|---|---|
| ocrmypdf_easyocr-0.3.0.tar.gz | 188.2 kB | With provenance | Details for ocrmypdf_easyocr-0.3.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| ocrmypdf_easyocr-0.3.0-py3-none-any.whl | Python 3 | none | any | Details for ocrmypdf_easyocr-0.3.0-py3-none-any.whl |
Total release size: 197.7 kB
Release files / ocrmypdf_easyocr-0.3.0.tar.gz
| Download URL | ocrmypdf_easyocr-0.3.0.tar.gz |
|---|---|
| Size | 188.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
0f9d2d28ca6eb5e32f07133bf8c94c0990c7f73af50d0480f6ec48b6bc6456a9
|
|
BLAKE2b-256 checksum How to use checksums |
a8002dd828cd51b38f72f570cd17c80bddca5c1bab55ccb5fa07b6ad44ad995c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jun 4, 2026.
Transparency logRelease files / ocrmypdf_easyocr-0.3.0-py3-none-any.whl
| Download URL | ocrmypdf_easyocr-0.3.0-py3-none-any.whl |
|---|---|
| Size | 9.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
22ebb336a70f9d0d598034fb52314a60b624d748759a140ab84be3d03697ba52
|
|
BLAKE2b-256 checksum How to use checksums |
3eaec7a20ae350d9d8d66f8f9e96036c54dc28b83463dba8f0372148ae3bb958
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jun 4, 2026.
Transparency logSecurity for ocrmypdf-easyocr 0.3.0
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.
Full provenance
Both files in this release have been uploaded with provenance metadata.
Attestation for ocrmypdf_easyocr-0.3.0.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jun 4, 2026.
Transparency logA 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.
