Indian Flag
Government Of India
A-
A
A+
Home/Models/AI4Bharat-IndicTrans2-Distilled-320M -Hindi (Devanagari)-to-Tamil: Language Translation Model
ownerNikhil Narasimhan
organizationAI4Bharat
ORGANISATION

AI4Bharat-IndicTrans2-Distilled-320M -Hindi (Devanagari)-to-Tamil: Language Translation Model

A high-performance neural machine translation (NMT) model for translating Hindi (Devanagari) to Tamil language, optimized with a 320M parameter size.

About Model

The IndicTrans2 Indic-to-Indic (320M) model by AI4Bharat is an advanced neural machine translation model designed to handle translations from Hindi(Devanagari) to Tamil. With a 320M parameter size, this model offers improved translation quality over smaller variants, while remaining computationally efficient for practical use cases. It leverages the latest advancements in transformer architecture, fine-tuned for high-quality cross-lingual transfer within the diverse set of Indic languages. IndicTrans2 is ideal for applications requiring multilingual support, such as content localization, educational tools, and cross-cultural communication, all while ensuring minimal latency.

AI4Bharat-IndicTrans2-Distilled-320M -Hindi (Devanagari)-to-Tamil: 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 13:21:19

Nikhil Narasimhan

0

Activity Overview Activity Overview

  • Downloads0
  • Redirect 12
  • File Size 0
  • Views 407

Tags Tags

  • Translation
  • Transformers
  • Indic-Trans
  • Multilingual
  • Tamil
  • Hindi

License Control License Control

MIT

More Models from AI4Bharat More Models from AI4Bharat

AI4Bharat- 500 M - RomanSetu Multilingual Native-to-Roman Model
RomanSetu is a multilingual continual pretrained transformer model designed for transliteration across six Indic languages
Instruction-Tuning
LLaMA2
Multilingual
Llama
  • See Upvoters1
  • Downloads51
  • File Size0
  • Views1,019
Updated 1 year(s) ago
AI4BHARAT
View Details
share
AI4Bharat- 400 M - RomanSetu Multilingual Native-to-Roman Model
RomanSetu is a multilingual continual pretrained transformer model designed for transliteration across six Indic languages
Multilingual
Llama
Instruction-Tuning
LLaMA2
  • See Upvoters1
  • Downloads89
  • File Size0
  • Views1,163
Updated 1 year(s) ago
AI4BHARAT
View Details
share
AI4Bharat- Maithili - IndicConformer Automatic Speech Recognition (ASR) Model
This model takes in mono-channel audio files at a 16,000 Hz sampling rate (WAV format) and outputs the transcribed text of the speech contained in the audio.
Automatic Speech Recognition
Speech-to-Text
NLP
  • See Upvoters0
  • Downloads29
  • File Size0
  • Views801
Updated 1 year(s) ago
AI4BHARAT
View Details
share
AI4Bharat- Konkani - IndicConformer Automatic Speech Recognition (ASR) Model
Automatic Speech Recognition (ASR) model for Konkani speech recognition, processing 16,000 KHz mono WAV audio and transcribing spoken content into text
Speech-to-Text
NLP
Automatic Speech Recognition
  • See Upvoters0
  • Downloads35
  • File Size0
  • Views803
Updated 1 year(s) ago
AI4BHARAT
View Details
share
AI4Bharat- Kashmiri - IndicConformer Automatic Speech Recognition (ASR) Model
This Automatic Speech Recognition (ASR) model transcribes Kashmiri speech from 16,000 KHz mono WAV audio files into text
Kashmiri
Speech-to-Text
NLP
Automatic Speech Recognition
  • See Upvoters0
  • Downloads28
  • File Size0
  • Views907
Updated 1 year(s) ago
AI4BHARAT
View Details
share
AI4Bharat - Romansetu-200M -Multilingual LLM for Indian langauges using romanization
RomanSetu is Efficiently unlocking multilingual (Indian Languages) capabilities of Large Language Models via Romanization.
Instruction-Tuning
LLaMA2
Llama
Multilingual
  • See Upvoters0
  • Downloads6
  • File Size0
  • Views326
Updated 1 year(s) ago
AI4BHARAT
View Details
share
AI4Bharat - Romansetu-100M - Multilingual LLM for Indian langauges using romanization
RomanSetu is Efficiently unlocking multilingual (Indian Languages) capabilities of Large Language Models via Romanization.
Llama
Multilingual
Instruction-Tuning
LLaMA2
  • See Upvoters0
  • Downloads11
  • File Size0
  • Views612
Updated 1 year(s) ago
AI4BHARAT
View Details
share
AI4Bharat- Kannada - IndicConformer Automatic Speech Recognition (ASR) Model
This Kannada Automatic Speech Recognition (ASR) model transcribes 16kHz mono-channel audio into text. It utilizes a Conformer-Large architecture with 120M parameters and a hybrid CTC-RNNT decoder for high-accuracy speech recognition.
Automatic Speech Recognition
Audio Processing
NLP
  • See Upvoters0
  • Downloads25
  • File Size0
  • Views916
Updated 1 year(s) ago
AI4BHARAT
View Details
share
AI4Bharat – Romanized Path – Base to Supervised Fine-Tuning (SFT)
Romansetu model is built on base pretrained model which is supervised fine tuned on instuction-following tasks using romanized Indian languages.
LLaMA2
Instruction-Tuning
Multilingual
Llama
  • See Upvoters0
  • Downloads3
  • File Size0
  • Views239
Updated 1 year(s) ago
AI4BHARAT
View Details
share
AI4Bharat-IndicTrans2 Large-1B -English-to-Hindi (Devanagari) – : Language Translation Model
A large-scale neural machine translation (NMT) model for translating English to Hindi (Devanagari) language, leveraging 1 billion parameters for high-quality translations.
Machine Translation
Transformer
low-resource-NLP
high-quality-translation
Large Model
cross-lingual
NLP
Multilingual
  • See Upvoters0
  • Downloads33
  • File Size0
  • Views1,035
Updated 1 year(s) ago
AI4BHARAT
View Details
share

© 2026 - Copyright AIKosh. All rights reserved.