Indian Flag
Government Of India
A-
A
A+

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.

About Model

The IndicTrans2 Indic-to-Indic (1B) model by AI4Bharat is a cutting-edge neural machine translation model designed to facilitate high-quality translations from Hindi (Devanagari) to Tamil. With a robust 1 billion parameter transformer architecture, this model ensures accurate, fluent, and contextually aware translations. It is optimized for cross-lingual understanding, making it valuable for applications such as multilingual content localization, education, and interregional communication in India. IndicTrans2 improves upon its predecessor with enhanced tokenization and multilingual training techniques, making it well-suited for low-resource Indic languages.

AI4Bharat-IndicTrans2-Hindi (Devanagari)-to-Tamil-Large-1B: Language Translation Model

Metadata Metadata

MIT

Jay Gala and Pranjal A Chitale and A K Raghavan and Varun Gumma and Sumanth Doddapaneni and Aswanth Kumar M and Janki Atul Nawale and Anupama Sujatha and Ratish Puduppully and Vivek Raghavan and Pratyush Kumar and Mitesh M Khapra and Raj Dabre and Anoop Kunchukuttan

text2text-translation

N.A.

Open

AI4Bharat

Sector Agnostic

21/02/25 13:21:21

0

Activity Overview Activity Overview

  • Downloads0
  • Redirect 0
  • Views 291
  • File Size 0

Tags Tags

  • Multilingual
  • Machine Translation
  • Hindi-Tamil
  • NLP
  • Transformer
  • Large Model
  • high-quality-translation
  • low-resource-NLP
  • cross-lingual

License Control License Control

MIT

Related Datasets Related Datasets

Updated 11 month(s) ago
2011 population census subdistrict polygon geometries
2011 population census subdistrict polygon geometries
Information
A geospatial dataset containing polygon geometries for subdistricts (Tehsils/Talukas) in India based on the 2011 Census
Census 2011
Administrative Maps
Spatial Statistics
Subdistrict Boundaries
Local Governance
  • See Upvoters0
  • Downloads22
  • File Size83.84 MB
  • Views594

DEVELOPMENT DATA LAB

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
  • Views209
Updated 3 month(s) ago

AI4BHARAT

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
  • Downloads204
  • File Size0
  • Views2,562
Updated 7 month(s) ago

AI4BHARAT

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
  • Downloads2
  • File Size0
  • Views166
Updated 11 month(s) ago

AI4BHARAT

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
  • Views98
Updated 11 month(s) ago

AI4BHARAT

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
  • Views48
Updated 11 month(s) ago

AI4BHARAT

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
  • Views67
Updated 11 month(s) ago

AI4BHARAT

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
  • Views57
Updated 11 month(s) ago

AI4BHARAT

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
  • Views49
Updated 11 month(s) ago

AI4BHARAT

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
  • Views292
Updated 11 month(s) ago

AI4BHARAT

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
  • Views149
Updated 11 month(s) ago

AI4BHARAT