A CLARIN Knowledge Centre hosted by the JPN National Centre of Excellence in the Humanities,
Indian Institute of Technology Indore — advancing multilingual digital humanities,
Indian language corpora, and scholarly publishing infrastructure.
The CLARIN K-Centre for Indian Language Innovation and Publishing Infrastructure (Indian-LIPI) is a specialised knowledge centre that provides expertise in multilingual digital scholarship and cultural digital heritage. The initiative is a joint effort of digital humanists at the JPN Centre and Digital Humanities and Publishing Research Group at IIT Indore. By combining expertise in language technologies, publishing studies, and digital humanities, Indian-LIPI supports researchers, archivists, and digital humanists working with Indian languages, textual archives, and publishing infrastructures. The centre aims to function as a regional and international hub for collaboration, training, and methodological support in multilingual digital research.
Mission
The Centre offers guidance and expertise in multilingual digital scholarship and cultural digital heritage practices. It supports research projects with digital texts, archives, and tools, and provides access to resources, training, and documentation. The Centre also hosts the Digital Humanities Intersections (DHI) journal, strengthening its role as a hub for digital humanities research — integrating AI and ML tools to publish issues in Indian languages.
Planned Services
The centre provides multilingual digital humanities support, including guidance on OCR, digitisation workflows, corpus creation, metadata enrichment, and text analysis. Users can access documentation, training materials, examples, and tools, as well as a helpdesk for project queries. The page also links to publications, datasets, ongoing initiatives, and service updates.
1.1 · Physical Infrastructure
Physical Infrastructure
Housed within IIT Indore’s main campus, the Centre’s physical infrastructure spans specialised laboratory spaces, scanning facilities, and seminar rooms designed for both technical operations and humanistic inquiry.
Digital Imaging Studio Lab
Equipped with the i2S CopiBook OS A2 Scanner — a professional-grade book scanner producing archival-quality digital images of manuscripts, documents, maps, and artefacts up to A2 size.
Active · Digitisation
Computing & OCR Infrastructure
Supports LIMB Processing Software for image processing and metadata management, and TESSERACT OCR for converting digitised materials into searchable, machine-readable text across multiple Indian scripts.
Active · Processing
Seminar & Workshop Spaces
Flexible seminar infrastructure supporting 9 major academic events since founding, including hybrid international workshops, PhD colloquia, and hands-on training sessions for up to 50+ participants.
Active · Events
Research & Reference Resources
Access to IIT Indore’s central library holdings, digital journal subscriptions, and specialised humanities databases, supplemented by Centre-specific collections in Digital Humanities and Environmental Humanities literature.
Active · Research Support
Publication Infrastructure — DHI Journal
Open-Access Journal · IIT Indore
Digital Humanities Intersections (DHI)
The Centre hosts the Digital Humanities Intersections journal — a peer-reviewed open-access publication advancing scholarship in multilingual digital humanities, publishing studies, and computational methods. Future issues will integrate AI and ML tools to publish in Indian languages, positioning DHI as a model for multilingual scholarly publishing infrastructure.
Students and researchers at the Centre work hands-on with professional digitisation tools — including the i2S CopiBook scanner, imaging workstations, LIMB processing software, and OCR workflows — to capture, process, and study Indian-language materials in the Digital Imaging Studio Lab.
Lab walkthrough — students using Centre digitisation tools
i2S CopiBook and imaging workstations in student useDocument capture and on-screen review
1.3 · Digital Infrastructure
Digital Infrastructure
The Centre’s digital stack is designed for long-term preservation, open access, and interoperability — aligned with FAIR principles (Findable, Accessible, Interoperable, Reusable).
Digital Infrastructure Pipeline
01
Acquisition & Capture
A2 High-res scanning
Audio-visual recording
Field documentation
Community-sourced materials
02
Processing & Annotation
LIMB image processing
TESSERACT OCR
Metadata tagging
Multilingual annotation
03
Archive & Storage
Multi-modal archive platform
Access control systems
Community governance
Long-term preservation
04
Publication & Access
DHI Open-Access Journal
Project websites
jpnnationalcentre.com
Public data repositories
05
Research & Re-use
NLP / computational analysis
Scholarly citation
Community access
Policy engagement
Server Infrastructure · HPE ProLiant
HPE ProLiant DL380 Gen11 · TPS1024 Configuration
The TPS1024-configured HPE ProLiant DL380 Gen11 server forms a core component of enterprise digital infrastructure, delivering high-performance compute, storage, and virtualisation capabilities. Designed for hybrid cloud, AI, and data-intensive workloads, it enables secure, scalable, and intelligently managed IT environments.
High-Performance ComputeVirtualisationHybrid Cloud ReadyAI & ML WorkloadsEnterprise Storage
1.4 · Human Infrastructure
Human Infrastructure
The Centre’s most important infrastructure is its people — a multidisciplinary team spanning Digital Humanities, Environmental Humanities, Social Sciences, and technical support, guided by national and international advisory bodies.
Digital Humanities
Computational Text AnalysisDigital ArchivingNLP & Corpus LinguisticsDigital Mapping (GIS)Multilingual DHCritical Digital Studies
Indian-LIPI serves as the primary broad portal for the following Indian languages, covering all aspects of language use, documentation, and digital infrastructure.
த
Tamil
Dravidian · ISO 639-1: ta
One of the oldest classical languages of India. Corpus building, OCR, and digitisation support for Tamil literary and archival materials.
മ
Malayalam
Dravidian · ISO 639-1: ml
Support for digital humanities workflows and text processing in Malayalam, including metadata enrichment and corpus annotation.
س
Sindhi
Indo-Aryan · ISO 639-1: sd
Focused expertise in Sindhi literature in post-partition India, marginalisation studies, and digital interventions for preservation.
ह
Hindi
Indo-Aryan · ISO 639-1: hi
Comprehensive coverage for India’s most widely spoken language including NLP resources, shared corpora, and pre-trained models.
ব
Bengali
Indo-Aryan · ISO 639-1: bn
Support for Bengali corpus creation, literary digitisation, and multilingual digital scholarship including diaspora writing.
A
English
Indo-European · ISO 639-1: en
Primary documentation language for all K-Centre services; support for multilingual comparative and translation studies.
Additional Language Expertise
The Centre has supported projects in marginal languages outside the 8th Schedule of the Indian Constitution:
AngikaPhaleeNaga LanguagesAssamese+ Other Minority Languages
Data Modalities & Linguistic Topics
Modalities Covered
TextImages (manuscripts, printed books)Audio (oral histories)Audio-visual (cultural practices)Multimodal Data
Linguistic Topics
Language DocumentationMultilingualismTranslation StudiesDiachronic Language StudiesCorpus-based AnalysisOpen Science Publishing
04 · Publications
Selected Publications
The JPN Centre brings a strong track record of peer-reviewed publications, edited volumes, and open-access digital scholarship spanning multilingual DH, digital cartography, corpus linguistics, and publishing studies.
01
Practices of Digital Humanities in India: Learning by Doing
Spatial Hypertexts or Hypermaps: A Proposal for Using Maps as Hypertexts in Geo-Spatial Archives
Justin, J., & Menon, N. · Journal of Map & Geography Libraries, 19(1–2) · 2023
08
Indian Electronic Literature Anthology
Menon, N., Shanmugapriya, T., Joseph, J., & Sutton, D. · IIT Indore KSHIP · 2023 · Open Access ↗
Access Resources & Services
To Access Resources & Services at Indian LIPI
Submit a query to request access to Indian LIPI's resources, datasets, tools, and documentation, or to explore collaboration and research opportunities. The K-Centre responds within 2 working days.
