Government Of India
A-
A
A+
Mizo OCR - Text Recognition for Mizo Language
OCR model for the Mizo language achieving 90.68% character accuracy on synthetic and curated printed text
About Model
MizoOCR is an Optical Character Recognition model for Mizo, a Tibeto-Burman language spoken by over 800,000 people in Mizoram, Northeast India. Built on TrOCR (microsoft/trocr-base-printed) and fine-tuned on a deduplicated dataset of 70,000 image-text pairs combining synthetic renders and curated samples, the model achieves 89.61% validation and 90.68% test character accuracy. MizoOCR correctly handles Mizo's unique diacritical characters (â, ê, î, ô, û) which cause failures in existing generic OCR systems. Developed by MWire Labs as part of the Northeast India OCR initiative to bring document digitization capabilities to underrepresented indigenous languages of the region.
Mizo OCR - Text Recognition for Mizo Language
Metadata
Attribution 4.0 International (CC BY- 4.0)
MWirelabs
OCR (Optical Character Recognition) Model
Transformers
Open
Sector Agnostic
25/02/26 12:33:50
0
Activity Overview
0
1 
21 
0
Tags
- OCR
- Mizo
- northeast-india
- trocr
- Image-to-Text
- low-resource
License Control
Attribution 4.0 International (CC BY- 4.0)
More Models from MWire Labs
Mizo OCR - Text Recognition for Mizo Language
OCR model for the Mizo language achieving 90.68% character accuracy on synthetic and curated printed text
OCR
low-resource
Image-to-Text
trocr
northeast-india
Mizo
- 0
- 1
- 0
22
Updated 2 day(s) ago
MWIRE LABS
NE-OCR
NE-OCR is a multilingual Optical Character Recognition model developed by MWire Labs to accurately recognize printed text from documents in Northeast Indian languages. The model supports Assamese, Bodo, English, Garo, Hindi, Khasi, Kokborok, Meitei (Bengali script), Meitei (Meitei Mayek script), Mizo, Nagamese, and Nyishi. It is designed to enable reliable digitization of books, newspapers, government records, educational materials, and cultural archives from Northeast India where mainstream OCR
Mizo
Garo
khasi
Nyishi
Kokborok
Nagamese
Printed Text Recognition
Northeast India OCR
Multilingual OCR
Optical Character Recognition
Meitei
BODO
OCR
northeast-india
doctr
vitstr
- 0
- 1
- 0
- 28
Updated 2 day(s) ago
MWIRE LABS
Nagamese Speech-to-Text
Automatic Speech Recognition (ASR) model for Nagamese speech, designed to transcribe spoken Nagamese into text for real-world usage.
ASR
Speech Recognition
low-resource-language
Nagamese
whisper
Automatic Speech Recognition
- 0
- 0
- 0
- 10
Updated 2 day(s) ago
MWIRE LABS
Garo OCR - Text Recognition for Garo
OCR model for the Garo language achieving 93.13% character accuracy.
Northeast Language Identification
NE-LID is a fast and accurate language identification model for Northeast Indian languages using character level features. It is designed for low resource and script diverse text and achieves high accuracy on short sentences.
fasttext
fastText
language identification
MWire Labs
Multilingual
low-resource
northeast-india
- 0
- 9
- 0
- 324
Updated 2 month(s) ago
MWIRE LABS
NortheastNER
NortheastNER is a token classification model built on XLM-RoBERTa and fine-tuned on ~25k sentences from gazetteers, news, and cultural texts across Northeast India. It detects region-specific entities, places, tribes, festivals, tourist sites, flora, fauna, and experimental local names; ideal for low-resource NER, regional search, cultural analytics, and knowledge graph applications.
Northeast India
Token Classification
NER
northeast-india
low-resource
XLM-RoBERTa
Meghalaya
Conservation
- 0
- 9
- 0
- 174
Updated 3 month(s) ago
MWIRE LABS
Kren-M
Northeast India's first AI language model. Kren-M is a 2.6B parameter bilingual model for Khasi-English, built on Gemma-2-2B. Features Kren-NE custom tokenizer covering 7 NE languages (Khasi, Garo, Mizo, Assamese, Manipuri, Nagamese, Nyishi) with 35.7% efficiency gain. Trained on 5.43M Khasi sentences. Capabilities: bidirectional translation, natural conversation, cultural context. Designed for language preservation across Northeast India
bilingual
Instruction-Tuning
continued-pretraining
low-resource
northeast-india
khasi
Tokenizer
Foundational model
Northeast India Languages
Kren-M
Northeast India
Indian Languages
Garo
- 0
- 19
- 0
- 515
Updated 3 month(s) ago
MWIRE LABS
NE-BERT
NE-BERT is Northeast India's first domain-specific multilingual foundation model. Built on the ModernBERT architecture and trained on 8.3 million sentences, it supports 9 regional languages: Assamese, Khasi, Garo, Manipuri (Meitei), Mizo, Nyishi, Nagamese, Kokborok, and Pnar. It achieves State-of-the-Art performance on regional benchmarks and offers 1.6x faster inference, bridging the digital divide for low-resource languages.
Pnar
modernbert
Masked Language Modeling
northeast-india
low-resource-NLP
northeast bert
mwirelabs
token-efficiency
Assamese
Garo
Nyishi
Meitei
Nagamese
khasi
A'chik
Mizo
kokborok
- 0
- 16
- 0
- 396
Updated 3 month(s) ago
MWIRE LABS
KhasiBERT
Khasi language model trained on 3.6M sentences using RoBERTa architecture. 110M parameters. Supports NLP tasks for Khasi text processing.
Meghalaya
roberta
Fill-Mask
khasi
Bert
masked-lm
foundational-model
low-resource
Indian Language
austroasiatic
kha
autotrain_compatible
endpoints_compatible
region:us
digital-india
safetensors
- 1
- 19
- 0
- 626
Updated 6 month(s) ago
MWIRE LABS
Khasi English Semantic Search Model
Khasi-English semantic search model, trained on 66,794 pairs with 0.69-0.74 similarity. ~90MB, supports Meghalaya tourism/culture. By MWirelabs
khasi-culture
text-embeddings-inference
autotrain_compatible
license:cc0-1.0
kha
en
Sentence Similarity
cross-lingual
semantic search
khasi
safetensors
sentence-transformers
Meghalaya
- 0
- 21
- 0
- 549
Updated 6 month(s) ago
MWIRE LABS
© 2026 - Copyright AIKosh. All rights reserved. This portal is developed by National e-Governance Division for AIKosh mission.