AI & ML interests
A group working towards furthering research in the field of Sanskrit Computational Linguistics
Recent Activity
Benchmarking models on Sanskrit Poetry to Hindi Prose Dataset
https://github.com/jivnesh/LCM
Official Collection the paper "A Novel Multi-Task Learning Approach for Context-Sensitive Compound Type Identification in Sanskrit"
A collection of models trained on sanskrit for semantic similarity
-
sanganaka/bge-m3-sanskritFT
Sentence Similarity • 0.6B • Updated • 560 -
sanganaka/gte-multilingual-base-sanskritFT
Sentence Similarity • 0.3B • Updated • 53 -
sanganaka/xlm-roberta-large-sanskritFT
Sentence Similarity • 0.6B • Updated • 92 -
sanganaka/LaBSE-sanskritFT
Sentence Similarity • 0.5B • Updated • 241
This collection contains all the datasets and models created by Sanganaka Labs of IIT Kharagpur related to Poetry Generation in various languages.
Dataset for the Chandomitra paper, EACL 2026 as well as future works. Code is available at https://github.com/sanganaka-iitkgp/chandomitra
Sanskrit Poetry to Prose Code: https://github.com/manojbalaji1/anvaya
https://github.com/Jivnesh/SanDP
This is a collection of files of paper "Free as in Free Word Order: An Energy Based Model for Word Segmentation and Morphological Tagging in Sanskrit"
This Hugging Face collection hosts models and datasets from DepNeCT — a dependency-based method for nested compound type identification in Sanskrit
This collection contains all the datasets and models created by Sanganaka Labs of IIT Kharagpur related to Poetry Generation in various languages.
Dataset for the Chandomitra paper, EACL 2026 as well as future works. Code is available at https://github.com/sanganaka-iitkgp/chandomitra
Benchmarking models on Sanskrit Poetry to Hindi Prose Dataset
Sanskrit Poetry to Prose Code: https://github.com/manojbalaji1/anvaya
https://github.com/jivnesh/LCM
https://github.com/Jivnesh/SanDP
This is a collection of files of paper "Free as in Free Word Order: An Energy Based Model for Word Segmentation and Morphological Tagging in Sanskrit"
Official Collection the paper "A Novel Multi-Task Learning Approach for Context-Sensitive Compound Type Identification in Sanskrit"
This Hugging Face collection hosts models and datasets from DepNeCT — a dependency-based method for nested compound type identification in Sanskrit
A collection of models trained on sanskrit for semantic similarity
-
sanganaka/bge-m3-sanskritFT
Sentence Similarity • 0.6B • Updated • 560 -
sanganaka/gte-multilingual-base-sanskritFT
Sentence Similarity • 0.3B • Updated • 53 -
sanganaka/xlm-roberta-large-sanskritFT
Sentence Similarity • 0.6B • Updated • 92 -
sanganaka/LaBSE-sanskritFT
Sentence Similarity • 0.5B • Updated • 241