Tibetan OCR: Tesseract on books and pecha, tested
94.3%
of letters on typeset book pages, with bod
Book pages read well, pecha pages do not
We ran Tesseract 5.5.4 on 38 proofread Tibetan pages from wikisource.org.
| Run | Book pages (11) | Pecha (27) |
|---|---|---|
| bod | 94.3% | 20.2% |
| bod best | 94.3% | 20.9% |
| bod, --psm 6 | 91.0% | 45.5% |
| bod best, --psm 6 | 90.9% | 48.9% |
| bod best, --psm 6, Sauvola | 92.9% | 46.6% |
| script/Tibetan best, --psm 6 | 88.9% | 44.6% |
| script/Tibetan, --psm 6 | 89.0% | 41.6% |
| dzo, --psm 6 | 81.8% | 34.4% |
The book pages come from 4 typeset books. The pecha pages come from 10 woodblock texts.
Letters are proofread letters found in order. Whole syllables right, best runs: 89.4% on book pages, 24.5% on pecha (Sauvola).
Book pages: the default command
brew install tesseract tesseract-lang
tesseract page.png page -l bod
It writes page.txt. Homebrew's tesseract-lang installs the fast bod, a 2.0 MB file.
bod best tied it at 94.3% and took longer: a median 2.9 s a page, against 2.4 s.
Leave the page mode alone here. --psm 6 cost 3.3 points
on book pages.
Pecha: add --psm 6 or lose pages
curl -LO https://raw.githubusercontent.com/tesseract-ocr/tessdata_best/4.1.0/bod.traineddata
mkdir -p tessdata && mv bod.traineddata tessdata/
tesseract pecha.png pecha --tessdata-dir tessdata -l bod --psm 6
In the default page mode, Tesseract wrote nothing on 10 of 27 pecha pages. On one, it printed:
Detected 788 diacritics
Empty page!!
--psm 6 reads the page as one block of text. With it, no
page came out empty, and bod read more letters on 23 of 27 pages.
bod best is an 8.6 MB file. It took a median 5.1 s a pecha page.
Red ink: try the Sauvola threshold
Seven of the 27 pecha pages are printed in red ink.
| Threshold | Red ink | Black ink |
|---|---|---|
| Default (Otsu) | 46.5% | 49.6% |
| Sauvola | 50.5% | 45.4% |
tesseract pecha.png pecha --tessdata-dir tessdata -l bod --psm 6 \
-c thresholding_method=2
Sauvola helped red ink and hurt black ink. Per text, bod best with --psm 6 read 40.8% to 61.2%.
The top slips: dropped vowels and ya
| Printed | Read as | Times |
|---|---|---|
| ◌ོ naro | Nothing | 106 |
| ◌ི gigu | Nothing | 78 |
| ◌ེ drengbu | Nothing | 69 |
| ◌ྱ subjoined ya | Nothing | 63 |
| ◌ི gigu | ◌ེ drengbu | 46 |
On book pages, the top slip of bod was ◌ི read as ◌ེ: 83 times.
A scanned PDF: the same split
ocrmypdf -l bod --sidecar book.txt scan.pdf book.pdf
For pecha, use bod best and the flag:
mkdir -p tessdata
cp -r "$(brew --prefix)/share/tessdata/configs" tessdata/
curl -L -o tessdata/bod.traineddata \
https://raw.githubusercontent.com/tesseract-ocr/tessdata_best/4.1.0/bod.traineddata
TESSDATA_PREFIX=$PWD/tessdata ocrmypdf -l bod --jobs 2 \
--tesseract-pagesegmode 6 \
--sidecar pecha.txt scan.pdf pecha.pdf
| Sidecar text | Text layer | |
|---|---|---|
| Book pages, bod, default | 93.9% | 90.9% |
| Pecha, bod best, --tesseract-pagesegmode 6 | 47.6% | 42.6% |
| Pecha, bod best, default | 35.7% | 30.5% |
The text layer is what pdftotext reads back from the output PDF. Search the sidecar file.
Time: 25.2 s for the book PDF, 81.6 s for the pecha PDF.
Six more things we checked
- No bod model can write ཎ ཥ ◌ཻ ◌ཽ and 15 other signs, most used in Sanskrit words. 153 letters on our pages cannot come out right.
- dzo (Dzongkha) has no ◌ཾ in its character set. Our pages hold 102.
- script/Tibetan wrote 2,922 Latin letters on pecha pages that hold none. bod wrote none.
- bod from the tessdata repo holds the same network as the fast bod, plus a config file.
- With --psm 6, a 2x upscale did not help: letters fell from 51.4% to 43.4% on a probe.
- Apple Vision on macOS 26.6 lists 30 languages, not Tibetan.
How we ran it
- bo.wikisource.org sends visitors to wikisource.org, which holds the Tibetan books. 778 of its 785 Tibetan books with 2 or more proofread pages have a wide first page, the pecha shape.
- Pages marked proofread, from a seeded shuffle of books, 3 a book (2 for some). Pages with footnotes, tables or unknown templates were left out.
- The 7 files with a book-shaped first page gave the 4 books of the book set.
- Of the other 3, one has no scans, one is over 80 MB, and one holds pecha pages.
- Pecha pages were drawn 3,000 px wide. Book pages were drawn at their scan width, 1,123 to 3,008 px.
- Scores count Tibetan letters, subjoined letters, vowel signs and marks. The tsheg, shad, digits, spaces and Latin letters are left out. A syllable is the letters between two tshegs or shads.
- Letters found in order is the longest common subsequence. Slips come from a second alignment, so counts are close, not exact.
- Models from tessdata_fast, tessdata_best and tessdata at tag 4.1.0.
- One thread a run, 2 runs at a time, at low priority, while other jobs ran. Times are rough.
- OCRmyPDF 17.13.0, pdftotext from Poppler 26.03.0. The PDFs hold the scans as JPEGs, one a page.
- Licenses: Tesseract and tessdata are Apache-2.0, OCRmyPDF is MPL-2.0. All 14 scan files are on Commons, marked public domain. We show no page images and quote no passage.
Scanned pages to text, no install
Run it yourself. Our Apify Actor turns a scanned PDF into Markdown or text. $0.006 a scanned page. It reads 18 languages, not Tibetan.
Or send us the scan. Tack, our AI, does the job for $29, up to 50 pages. First page free. For Tibetan, ask first.
Questions people ask
Does Tesseract support Tibetan?
Yes, with bod, script/Tibetan or dzo. On our 11 typeset book pages, bod read 94.3% of letters with no flags.
Why does Tesseract return an empty page?
On woodblock pecha, the default page mode wrote nothing on 10 of 27 pages. Add --psm 6.
Which Tesseract model is best for Tibetan?
On book pages, bod and bod best tie at 94.3%. On pecha, bod best with --psm 6 read the most letters, 48.9%.
Can I OCR a Tibetan PDF?
Yes. OCRmyPDF with -l bod found 93.9% of letters on our book pages. For pecha, use bod best and add --tesseract-pagesegmode 6 (47.6% of letters).
Is Tesseract good enough for pecha?
Not for a clean text. On our 27 pecha pages, the best run got 48.9% of letters and 20.1% of whole syllables right. We did not test other OCR tools.
Related guides
- Punjabi OCR, tested: free Tesseract models on 28 scans
- Sanskrit OCR, tested: free Tesseract models on 30 scans
- Tesseract psm modes: which one to use, tested (2026)
- How to make a PDF searchable: scanned PDFs, tested
- Screenshot OCR, tested: Tesseract, Apple Vision and RapidOCR on 32 screenshots
- Marathi OCR, tested: free Tesseract models on 30 scans