snowfluke/ppu-indra-ocr-models

Indra OCR models (mirror)

This repository is an unmodified mirror of the Indra OCR model weights. The weights are created and owned by Datalab.

• Original model: datalab-to/indra-ocr
• Revision mirrored: commit d7c839c892bfe4b8993373db64c62f154d05d70b (tag v3.1)
• Changes: none. Every file is byte-identical to the original revision.
• License: Datalab's modified AI Pubs Open RAIL-M license, in LICENSE. It is distributed here unchanged and governs every file in this repository.

This mirror is maintained by the community project ppu-indra-ocr, a TypeScript inference library. Datalab does not endorse this mirror or that project. For the official models, use Datalab's repository above.

Read the license before you use these weights

By downloading or using these weights, you agree to the license in LICENSE, including its use-based restrictions in paragraph 5 and Attachment A. If you pass the weights on, or run a service on them for others, you must bind your own users to the same restrictions and give them a copy of the license (Section 4). Attachment A, quoted from the license:

As conditions to the Licenses set forth in this Agreement, You agree not to use, reproduce, modify, create or Distribute the Model, Derivatives of the Model, or Output (collectively, "Use") in any of the following ways:

1. Legal: (a) In any way that violates any applicable national, federal, state, local or international law or regulation; or (b) to directly or indirectly infringe or misappropriate any third party intellectual property rights (including those of Licensor or any Contributor)
2. Commercial: (a) for any purpose if You (your employer, or the entity you are affiliated with) generated more than twenty million US Dollars ($20,000,000) in gross revenue in the prior year, except where Your Use is limited to personal use or research purposes; (b) for any purpose if You (your employer, or the entity you are affiliated with) has raised more than twenty million US dollars ($20,000,000) in total equity or debt funding from any source, except where Your Use is limited to personal use or research purposes; or (c) for any purpose if You (your employer, or the entity you are affiliated with) provides or otherwise makes available any product or service that competes with any product or service offered by or made available by Licensor or any of its affiliates.

Commercial and broader use licenses may be available from Licensor at the following URL: https://www.datalab.to/

Section 8 of the license applies the same license to the Output of the model.

Files

File	Role
det.onnx	text line detector
rec.onnx	Latin-script line recognizer
rec_cjk.onnx	Chinese line recognizer
script.onnx	script classifier (routes Chinese lines)
orient.onnx	page orientation
order.onnx	reading order and layout
meta.json	vocabularies and input settings
mathcls.onnx, math_enc.onnx, math_dec_init.onnx, math_dec_step.onnx, math_meta.json	math reader (inline LaTeX)

Attribution

Indra OCR by Datalab. Original model: https://huggingface.co/datalab-to/indra-ocr. Source code: https://github.com/datalab-to/indra (Apache-2.0). License: LICENSE. No changes were made to the model files.

The status of this mirror, and the request we sent Datalab about it, are recorded in LICENSE-STATUS.md. We remove this mirror if Datalab asks.