indic-ocr

Document parsing for English and 22 Indian languages, printed and handwritten. A page image in; reading-ordered Markdown out, with math as LaTeX and tables as HTML or Markdown, plus per-block JSON.

IndicOCR reads a document page and returns its text in reading order. It is a modular, two-stage parser: IndicDocLayout detects the blocks on the page and orders them, and IndicBlockOCR transcribes the textual blocks. The two stages communicate through a structured JSON file, so either stage can be used independently or replaced with another implementation.

ARCHITECTURE.md traces one page through the whole call path, names what each module does, and lists the invariants that break the output silently when violated.

Detected blocks with their reading order on the left, the transcription on the right.

IndicBlockOCR uses the Sarvam-30B tokenizer, with a vocabulary designed to cover Indian scripts. IndicDocLayout is a fine-tune of PP-DocLayoutV3/RT-DETR, trained with a 37-class taxonomy designed for education-domain documents.

IndicDocLayout predicts a labelled bounding box for each detected layout element. The 37 supported labels are:

Advertisement, Answer, Author, Chapter-end-section, Chapter-title, Chart, Code, Contact-info, Dateline, Diagram, Equation, Expression, Flag, Folio, Footer, Footnote, Header, Image, Image-caption, Index, Infobox, List, MCQ, Page-number, Paragraph, Placeholder-text, Question, Reference, Section-title, Solved-example, Sub-section-title, Sub-sub-section-title, Table, Table-caption, Table-of-contents, Title, Website-link

Printed page recognition is supported across English and the 22 constitutionally recognised Indian languages: Assamese, Bengali, Bodo, Dogri, Gujarati, Hindi, Kannada, Kashmiri, Konkani, Maithili, Malayalam, Manipuri, Marathi, Nepali, Odia, Punjabi, Sanskrit, Santali, Sindhi, Tamil, Telugu, Urdu.

Handwriting recognition currently supports English and 12 Indian languages: Hindi, Bengali, Telugu, Marathi, Tamil, Gujarati, Kannada, Malayalam, Odia, Punjabi, Assamese, and Urdu.

Handwriting quality is still a work in progress, particularly across different writing styles. We are working on improving recognition and extending support to additional languages.

The repo ships an installer that reads your driver and picks matching CUDA wheels. If you work in a virtual environment, please activate it first, as the installer installs into whichever Python is active.

IDP=$(python -c "from huggingface_hub import snapshot_download as d; print(d('bodhan-ai/indic-ocr'))")
cd "$IDP" && ./install.sh

It will use uv if that is available, and pip otherwise. Where running a shell script is not convenient, TROUBLESHOOTING.md lists the two commands it runs.

import sys
from huggingface_hub import snapshot_download

repo = snapshot_download("bodhan-ai/indic-ocr")
sys.path.insert(0, repo)                    # the code ships in the repo
from indic_ocr import IndicOCR

parser = IndicOCR.from_pretrained(repo)

page = parser.parse("page.png")
print(page["markdown"])                     # reading-ordered Markdown

page also carries the per-block detail, which you can save as follows:

import json

with open("page.json", "w", encoding="utf-8") as f:
    json.dump(page, f, ensure_ascii=False, indent=2)

To run the two stages separately:

from indic_ocr import IndicDocLayout, IndicBlockOCR

layout = IndicDocLayout(f"{repo}/weights/layout").detect("page.png")
page = IndicBlockOCR(f"{repo}/weights/ocr").run("page.png", layout)

run() takes a layout object, a dict, or the path to a layout JSON file.

parser.parse("page.png") returns the page metadata and its blocks in reading order:

{
  "image": "sample1.png",
  "width": 800,
  "height": 1273,
  "blocks": [
    {"order": 0, "label": "Header", "type": "PageHeader",
     "bbox_xyxy": [345.6, 51.7, 437.1, 114.7], "conf": 0.6, "text": ""},
    {"order": 1, "label": "Page-number", "type": "PageNumber",
     "bbox_xyxy": [367.8, 78.9, 413.2, 107.4], "conf": 0.747, "text": "229"},
    {"order": 2, "label": "Paragraph", "type": "Text",
     "bbox_xyxy": [77.9, 121.3, 711.8, 199.4], "conf": 0.863,
     "text": "Thus we see that, if we can prove that twice the L.H.S. of (30) ..."}
  ]
}

Note: Figures, charts, advertisements, running headers, and footers are not sent through the recognizer by default. They remain in the JSON with text: "", so you can see what was detected and where. Page numbers and other margin text such as folios are transcribed.

Machine-readable JSON Schema for each envelope, in schemas/:

A layout from your own detector must use a label from the 37-class taxonomy, or declare type explicitly. An unrecognised label is rejected rather than silently read as prose.

Tables come back as HTML by default. Choose the format when you construct the parser:

parser = IndicOCR.from_pretrained(repo)                          # HTML (default)
parser = IndicOCR.from_pretrained(repo, table_format="markdown") # Markdown

Word-level accuracy, reported as 100 x (1 - WER).

Word-level accuracy, reported as 100 x (1 - WER).

Reading order remains a challenge for complex, multi-column layouts. Handwriting recognition is also still being improved, particularly across different writing styles and writing characteristics.

We are also extending handwriting support to additional Indic languages.

We benchmarked our end-to-end pipeline with vLLM on a single NVIDIA H100 80GB GPU using a diverse mix of documents (math, tables, handwritten notes, research papers, multi-column, and even complex newspaper layouts) from the OmniDocBench V1.6 benchmark set (official english subset).

Released under Indic Open Model License v1.0.

The release incorporates components distributed under Apache 2.0, including PP-DocLayoutV3, Qwen3.5, and the Sarvam-30B tokenizer. See the repository license and the corresponding upstream licenses for the applicable terms and attribution requirements.

If you find the license difficult to understand, here is a plain-language guide to the Indic Open Model License.

Broad, no-cost access for research, government, nonprofit, and commercial use — with a few conditions attached.

This deed is a human-readable summary of the license, not a substitute for it. Where the two disagree, the full Indic Open Model License governs.

You're free to

No cost, no royalty, worldwide — for research, government, nonprofit, and commercial use, at any scale.

• ✅ Run it — for inference, in a product, in research, however you like.
• ✅ Change it — fine-tune, distill, quantize, merge, or otherwise build on it.
• ✅ Self-host it — power your own product or service with it, commercial or not.
• ✅ Share it — pass on copies of the model or your own version of it.

As long as you

Five conditions cover almost everything. The rest of the license is these, spelled out in legal detail.

1. Give credit

Wherever you ship the model or a derivative to anyone else, say where it came from — and don't strip out existing notices.

"Built with [Model Name] from Bodhan AI / AI4Bharat."

2. Pass it on the same way

If you give your fine-tuned or derived version to anyone else — hand it over, or run it as a service for them — it carries this exact license. You can't relicense it on different terms.

3. Ask before hosting it for others

Self-hosting is free. But if you're going to run it as an API or hosted service that other people or companies call directly, that needs Bodhan AI's written sign-off first — unless you're a nonprofit, government, or academic user, or you publicly release an equally capable open version within 90 days.

4. Don't use it to cause harm

No exceptions — not even for nonprofit or research use. That means no:

• child sexual abuse material, or content that sexualizes minors
• weapons development, including chemical, biological, radiological, or nuclear
• mass surveillance or social-scoring systems
• disinformation campaigns, including election manipulation
• automated decisions that affect someone's legal rights without human oversight
• deepfakes or voice clones of real people without their consent
• robocalls, auto-dialers, or voice-phishing scams
• AI companion products designed to simulate romance or foster emotional dependency

5. Talk to us if your product gets huge

If your own product built on this — not through hosting it for others, that's covered above — crosses either threshold, you'll need a separate commercial license. Doesn't apply to nonprofit, government, or academic users.

@misc{indicocr2026,
  title  = {IndicOCR: Multilingual Document Parsing for English and 22 Indian Languages},
  author = {Bodhan AI and AI4Bharat},
  year   = {2026},
  url    = {https://bodhan.ai/research/blogs/indic-ocr}
}