An official initiative by SHEDA, Government of Sikkim — combining privacy-first local OCR with expert human review to preserve and transcribe ancient Tibetan manuscripts. Open to the public and students via login-based read access.
Sutra Digitizer is an official initiative by SHEDA (Department of Ecclesiastical Affairs), Government of Sikkim, built to digitize, transcribe, and preserve ancient Buddhist sutras — particularly Tibetan manuscripts that hold centuries of spiritual and cultural wisdom.
Using privacy-first local OCR engines (no data leaves the server) paired with an intuitive collaborative workbench, our platform enables scholars, monks, translators, and researchers to work together seamlessly. Students and the public can access digitized sutras through login-based read-only access. Each page is carefully processed, reviewed, and archived to ensure accuracy and longevity.
These tools are used internally by our team of scholars, translators, and reviewers. Registered students and the public can browse the digitized sutras through read-only access.
Privacy-first OCR running entirely on local servers — specialized models for Tibetan scripts. No data ever leaves the premises.
Internal side-by-side manuscript viewing with real-time transcription editing, zoom controls, rotation, and a rich metadata panel — used by authorized team members only.
Admins, Managers (Teachers), Translators, and Reviewers collaborate on digitization. Students and the public get login-based read-only access.
Internal organization of sutras into projects with chapters and pages. Track progress with OCR status indicators and thumbnail previews.
Every internal action is logged — page edits, metadata changes, OCR runs — with detailed before/after comparison for complete accountability.
A streamlined four-step process that turns physical sutras into searchable, preserved digital texts.
Scan and upload manuscript pages as high-resolution images with batch upload support.
On-premise OCR engines extract text from manuscript images — your data never leaves the server.
Experts review OCR results in the side-by-side workbench and correct any errors.
Finalized transcriptions are stored in a searchable digital archive, preserved forever.
To make ancient Buddhist sutras accessible to the world by providing a state-of-the-art digitization platform, led by SHEDA, Government of Sikkim, that combines privacy-first local OCR technology with human expertise.
A world where no sacred text is lost to time. We envision a complete digital library of Buddhist sutras — digitized by our internal team and made available for scholars, practitioners, students, and the public to view and study.
Got questions? We've got answers. If you don't find what you're looking for, reach out to us.
Students and the public can sign in to browse the growing collection of digitized Buddhist sutras. Scholars and translators can request contributor access to join our internal team.