ଓOpenOdia

Directory

Every Odia project, in one place.

Open-source repos, datasets, models, fonts, libraries, and tools — curated from Awesome-Odia-AI and the Odia GitHub organisations, filterable by license and citable in one click.

★ Featuredrotates every Monday
Python

sovogpt

Experimental code for Odia language LLM using consumer hardware.

20Python
Jupyter Notebook

nlp-for-odia

State of the Art Language models and Classifier for Odia, which is spoken in the Indian state of Odisha

14Jupyter Notebook
Also worth a look

openodia

8Python

odlang

6Go

OdiaLingua

6TypeScript
TranslationCurated

Sua

Machine Translation from English to Odia language

GPL-3.0Cite
TranslationCurated

IndicTrans

NLP · Translation

No licenseCite
TranslationCurated

IndicTrans2

NLP · Translation

No licenseCite
TranslationCurated

WAT 2025 NLLB-200 Fine-tuned Model

A highly optimized 3.3B parameter neural machine translation model scored on WAT 2025.

No licenseCite
TranslationCurated

NLTM-EILMT Bhashini Translation API System

The sovereign, Bhashini-backed open-source repository providing robust, production-ready bi-directional API/REST endpoints for English to Odia machine translation.

CC-BY-4.0Cite
TranslationCurated

mo-odia-translator

English↔Odia translation model based on mT5 (300M params, Apache-2.0).

Apache-2.0Cite
TranslationCurated

qwen3-eng-odia-translation

Qwen3-based English-to-Odia translation model fine-tuned for conversational translation (752M params).

No licenseCite
TransliterationCurated

IndicXlit

NLP · Transliteration

No licenseCite
TransliterationCurated

open-source unicode converter

to transliterate between various languages to Odia language .

GPL-3.0Cite
DatasetsCurated

IndicCorp

Large sentence-level monolingual corpora for 11 Indian languages and Indian English containing 8.5 billions words (250 million sentences) from multiple news domain sources.

No licenseCite
DatasetsCurated

Naamapadam

Training and evaluation datasets for named entity recognition in multiple Indian language.

No licenseCite
DatasetsCurated

IndicCorp v2

he largest collection of texts for Indic languages consisting of 20.9 billion tokens of which 14.4B tokens correspond to 23 Indic languages and 6.5B tokens of Indian English content curated from Indian websites.

No licenseCite
DatasetsCurated

L3Cube-IndicSQuAD (Odia)

A meticulously engineered, 118,000+ sample extractive Question Answering dataset.

CC-BY-4.0Cite
Language ModelCurated

Language Model

Pretrained Odia Language Model.

MITCite
Language ModelCurated

BertOdia

Bert-based Odia Language Model.

No licenseCite
Language ModelCurated

IndicBERT

Multilingual, compact ALBERT language model trained on IndicCorp covering 11 major Indian and English. Small model (18 million parameters) that is competitive with large LMs for Indian language tasks.

No licenseCite
Language ModelCurated

IndicNER

Named Entity Recognizer models for multiple Indian languages. The models are trained on the Naampadam NER dataset mined from Samanantar parallel corpora.

No licenseCite
Language ModelCurated

IndicBERTv2

Language model trained on IndicCorp v2 with competitive performance on IndicXTREME

No licenseCite
Language ModelCurated

Oriya-BERT-SQuAD

A highly capable 0.2B parameter OdiaBERT model rigorously fine-tuned directly on the IndicSQuAD dataset.

CC-BY-4.0Cite
Language ModelCurated

odia-bert

A fill-mask BERT model (753+ downloads) specifically pretrained for Odia language understanding tasks.

CC-BY-4.0Cite
Word EmbeddingCurated

FastText (CommonCrawl + Wikipedia)

Pretrained Word vector (CommonCrawl + Wikipedia). Trained on Common Crawl and Wikipedia using fastText. Select the language "oriya" from the model list.

No licenseCite
Word EmbeddingCurated

FastText (Wikipedia)

Pretrained Word vector (Wikipedia). Trained on Wikipedia using fastText. Select the language "oriya" from the model list.

No licenseCite
Word EmbeddingCurated

IndicFT

Word embeddings for 11 Indian languages trained on IndicCorp. The embeddings are based on the fastText model and are well suited for the morphologically rich nature of Indic languages.

No licenseCite
Word EmbeddingCurated

odia-sentence-similarity-sbert

Sentence-BERT model for Odia semantic similarity and sentence embedding.

CC-BY-4.0Cite
Word EmbeddingCurated

odia-sentence-bert-nli

Sentence-BERT model fine-tuned on Natural Language Inference for Odia sentence embeddings.

CC-BY-4.0Cite
MorphanalyzersCurated

IndicNLP Morphanalyzers

Unsupervised morphanalyzers for 10 Indian languages including Odia learnt using morfessor.

No licenseCite
Instruction SetCurated

Odia master data llama2

This dataset contains 180k Odia instruction sets translated from open-source instruction sets and Odia domain knowledge instruction sets.

CC-BY-NC-SA-4.0Cite
Instruction SetCurated

Odia context 10k llama2 set

This dataset contains 10K instructions that span various facets of Odisha's unique identity. The instructions cover a wide array of subjects, ranging from the culinary delights in 'RECIPES,' the historical significance of 'HISTORICAL PLACES,' and 'TEMPLES OF ODISHA,' to the in…

CC-BY-NC-SA-4.0Cite
Instruction SetCurated

Roleplay Odia

This dataset contains 1k Odia role play instruction set in conversation format.

No licenseCite
Instruction SetCurated

OdiEnCorp translation instructions 25k

This dataset contains 25k English-to-Odia translation instruction set.

CC-BY-NC-SA-4.0Cite

Showing 30 of 194 projects