Indian Flag
Government Of India
A-
A
A+
Home/Models/AI4Bharat - MultiIndic Model for Sentence Summarization (Sentence Specific)

AI4Bharat - MultiIndic Model for Sentence Summarization (Sentence Specific)

It is a multilingual, sequence-to-sequence pre-trained model fine-tuned on the IndicSentenceSummarization dataset for summarization across 11 Indian languages.

About Model

It is a sequence-to-sequence pre-trained model based on IndicBART, fine-tuned on the IndicSentenceSummarization dataset, supporting 11 Indian languages: Hindi, Marathi, Punjabi, Tamil, Telugu, Bengali, Gujarati etc. Smaller than mBART and mT5, it is computationally more efficient for decoding. Trained on a vast corpus of 5.53 million sentences, each language is represented in its own script, removing the need for script mapping to/from Devanagari, making it ideal for summarization tasks across various Indian languages.

AI4Bharat - MultiIndic Model for Sentence Summarization (Sentence Specific)

Metadata Metadata

MIT

Aman Kumar, Himani Shrotriya, Prachi Sahu, Raj Dabre, Ratish Puduppully, Anoop Kunchukuttan, Amogh Mishra, Mitesh M. Khapra, Pratyush Kumar

Text Summarization

N.A.

Open

AI4Bharat

Sector Agnostic

21/02/25 13:20:56

Nikhil Narasimhan

0

Activity Overview Activity Overview

  • Downloads0
  • Redirect 0
  • File Size 0
  • Views 129

Tags Tags

  • Multilingual
  • AI4Bharat
  • NLP
  • Deep Learning
  • Text Summarization

License Control License Control

MIT

Related Models Related Models

AI4Bharat - MultiIndic WikiBio Structured Summarization Model
MultiIndicWikiBioSS is a multilingual sequence-to-sequence model fine-tuned on the IndicWikiBio dataset for nine Indian languages
Transformers
Multilingual
NLP
Text2Text Generation
  • See Upvoters0
  • Downloads0
  • File Size0
  • Views55
Updated 1 year(s) ago
AI4BHARAT
View Details
share

More Models from AI4Bharat More Models from AI4Bharat

AI4Bharat - IndicBART: Multilingual Sequence-to-Sequence Model
A BART-based model pre-trained for various sequence-to-sequence tasks across multiple Indian languages.
BART
Multilingual
Indian Languages
NLP
Sequence-to-Sequence
  • See Upvoters1
  • Downloads16
  • File Size0
  • Views225
Updated 4 month(s) ago
AI4BHARAT
View Details
share
AI4Bharat - Airavata: Large-Scale Multilingual Model for Indic Languages
A model designed to convert text into speech, supporting multiple Indian languages.
Text to Speech
Speech Synthesis
Accessibility
Indian Languages
  • See Upvoters3
  • Downloads207
  • File Size0
  • Views2,654
Updated 8 month(s) ago
AI4BHARAT
View Details
share
AI4Bharat - MultiIndic Model for Sentence-level Question Generation
MultiIndicQuestionGenerationSS is a multilingual, sequence-to-sequence pre-trained model fine-tuned on the IndicQuestionGeneration dataset for question generation across 11 Indian languages.
NLP
Deep Learning
Question Generation
Text Generation
Multilingual
AI4Bharat
  • See Upvoters0
  • Downloads3
  • File Size0
  • Views204
Updated 1 year(s) ago
AI4BHARAT
View Details
share
AI4Bharat - MultiIndic Model for Sentence Summarization (Sentence Specific)
It is a multilingual, sequence-to-sequence pre-trained model fine-tuned on the IndicSentenceSummarization dataset for summarization across 11 Indian languages.
Deep Learning
Text Summarization
Multilingual
AI4Bharat
NLP
  • See Upvoters0
  • Downloads0
  • File Size0
  • Views130
Updated 1 year(s) ago
AI4BHARAT
View Details
share
AI4Bharat - MultiIndic WikiBio Structured Summarization Model
MultiIndicWikiBioSS is a multilingual sequence-to-sequence model fine-tuned on the IndicWikiBio dataset for nine Indian languages
Multilingual
Text2Text Generation
Transformers
NLP
  • See Upvoters0
  • Downloads0
  • File Size0
  • Views55
Updated 1 year(s) ago
AI4BHARAT
View Details
share
AI4Bharat-VITS-Rasa-13: Text to Speech Model
A Text-to-Speech (TTS) model optimized for use with the Rasa conversational AI framework, built using the VITS (Variational Inference Text-to-Speech) architecture to generate natural-sounding speech in multiple Indic languages.
Rasa-framework
Text to Speech
Indic Languages
NLP
multilingual-TTS
VITS
AI-voice
chatbot
conversational-AI
Speech Synthesis
  • See Upvoters1
  • Downloads6
  • File Size0
  • Views72
Updated 1 year(s) ago
AI4BHARAT
View Details
share
AI4Bharat - MultiIndic Model for Sentence Summarization (General)
It is a multilingual, sequence-to-sequence pre-trained model fine-tuned on the IndicSentenceSummarization dataset for sentence summarization across 11 Indian languages.
AI4Bharat
Multilingual
Text Summarization
Deep Learning
NLP
  • See Upvoters0
  • Downloads1
  • File Size0
  • Views65
Updated 1 year(s) ago
AI4BHARAT
View Details
share
AI4Bharat-IndicConformer-STT-SAT-Hybrid-CTC-RNNT-Large (Santali): Automatic Speech Recognition Model
A large-scale Automatic Speech Recognition (ASR) model for Santali, utilizing a hybrid CTC-RNNT decoder.
Neural Networks
Speech Recognition
Hybrid-CTC-RNNT
Indic Languages
ASR
Automatic Speech Recognition
Deep Learning
Speech-to-Text
Conformer
  • See Upvoters1
  • Downloads1
  • File Size0
  • Views66
Updated 1 year(s) ago
AI4BHARAT
View Details
share
AI4Bharat-IndicTrans2-Hindi (Devanagari)-to-Tamil-Large-1B: Language Translation Model
A large-scale neural machine translation (NMT) model for translating from Hindi (Devanagari) to Tamil languages, leveraging 1 billion parameters for high-quality translation.
Multilingual
low-resource-NLP
high-quality-translation
Large Model
Transformer
NLP
Hindi-Tamil
Machine Translation
cross-lingual
  • See Upvoters0
  • Downloads0
  • File Size0
  • Views365
Updated 1 year(s) ago
AI4BHARAT
View Details
share
AI4Bharat-IndicConformer-STT-TA-Hybrid-CTC-RNNT-Large (Tamil): Autmatic Speech Recognition Model
A large-scale Automatic Speech Recognition (ASR) model for Tamil, utilizing a hybrid CTC-RNNT decoder.
Hybrid-CTC-RNNT
Speech Recognition
Neural Networks
Conformer
Speech-to-Text
Deep Learning
Indic Languages
ASR
AI4Bharat
Automatic Speech Recognition
Tamil
  • See Upvoters0
  • Downloads6
  • File Size0
  • Views164
Updated 1 year(s) ago
AI4BHARAT
View Details
share

© 2026 - Copyright AIKosh. All rights reserved. This portal is developed by National e-Governance Division for AIKosh mission.