Vyakyarth - Multilingual Sentence Embedding Model
Vyakyarth is a sentence-transformers-based model fine-tuned for Indic languages, capable of mapping text to a 768-dimensional dense vector space for semantic search, similarity, classification, and clustering tasks.
About Model
Vyakyarth is a multilingual sentence embedding model designed for Indic languages. Developed by Krutrim AI Labs, it is fine-tuned from stsb-xlm-r-multilingual, leveraging sentence-transformers to encode sentences and paragraphs into 768-dimensional embeddings. The model supports a wide range of NLP tasks, including semantic textual similarity, semantic search, paraphrase mining, text classification, and clustering. Built on XLM-RoBERTa, Vyakyarth ensures high-quality representations across multiple Indian languages, making it ideal for applications in search engines, recommendation systems, and multilingual NLP research.
Vyakyarth - Multilingual Sentence Embedding Model
Metadata
Krutrim Community License Agreement Version 1.0
Ola Krutrim
Large Language Models
N.A.
Open
Sector Agnostic
28/02/25 07:00:46
0
Activity Overview
0
45 
0 
845
Tags
- NLP
- Indic Languages
- Multilingual AI
- Deep Learning
- Krutrim AI
- paraphrase mining
- semantic search
- text similarity
- sentence embedding
- XLM-RoBERTa
License Control
Krutrim Community License Agreement Version 1.0
More Models from Ola Krutrim
- 0
- 49
- 0
1,304
- 0
- 144
- 0
- 3,041
- 0
- 45
- 0
- 846
- 1
- 136
- 0
- 1,688
- 0
- 33
- 0
- 663
- 0
- 27
- 0
- 810
© 2026 - Copyright AIKosh. All rights reserved.