Skip to main content
Pre-release

This release is a pre-release and may not be stable for production use.

turboocr-engine-openvino

The Intel build of the TurboOCR engine. Identical Python API to turboocr-engine-cpu — from turboocr_engine import OCR, or from turboocr import OCR through the pure-Python turboocr umbrella (pip install "turboocr[openvino]" installs both) — with the Intel backend compiled into the native extension. backend="openvino" (or "intel") runs the native OpenVINO Runtime engine; backend="cpu" is the plain ONNX Runtime fallback in the same wheel.

The OpenVINO runtime itself arrives as this wheel's own pip dependency (openvino>=2026.2,<2026.3) and is found automatically — no system OpenVINO install and no LD_LIBRARY_PATH needed.

One binary covers Intel CPU, iGPU, Arc and NPU; pick the device at RUN time with OCR(backend="openvino", device="GPU") or the OV_DEVICE environment variable (CPU | GPU | NPU), so an iGPU laptop and a discrete Arc box run the same wheel.

Install exactly one turboocr-engine-* wheel per environment: they all provide the turboocr_engine import package and link mutually incompatible ONNX Runtime builds. turboocr doctor reports which engine the installed wheel actually carries.

Metadata

Release files for turboocr-engine-openvino 4.0.0a8

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Built distribution (wheel)

Table of built distributions (wheels) for turboocr-engine-openvino 4.0.0a8
File Interpreter ABI Platform
turboocr_engine_openvino-4.0.0a8-cp312-abi3-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl CPython 3.12 abi3 Linux glibc 2.27+ x86-64, Linux glibc 2.28+ x86-64 Details

Release files / turboocr_engine_openvino-4.0.0a8-cp312-abi3-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl

Download URL turboocr_engine_openvino-4.0.0a8-cp312-abi3-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
Size 20.3 MB
Tags CPython 3.12 Linux glibc 2.27+ x86-64 Linux glibc 2.28+ x86-64 abi3
SHA-256 checksum
How to use checksums
c31089e6287e403c8e0131ad0469e42f0a04bd723dbbd4a88fb99b9dbc455d1e
BLAKE2b-256 checksum
How to use checksums
e72947f2aff5791623e532b75e1349c48931e6ea2dda84bf5ab2a640f4f722d3
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

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 Sep 1, 2026.

Transparency log
Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page