Government Of India
A-
A
A+
AI4Bharat- 400 M - RomanSetu Multilingual Native-to-Roman Model
RomanSetu is a multilingual continual pretrained transformer model designed for transliteration across six Indic languages
About Model
RomanSetu-native is a multilingual continual pretrained transformer model built on Llama 2, RomanSetu-native is pretrained on native-script corpora for the same six Indic languages(Hindi,Marathi,Gujarati,Tamil,Malayalam) and instruction-tuned to produce high-quality romanized outputs.
AI4Bharat- 400 M - RomanSetu Multilingual Native-to-Roman Model
Metadata
Llama 2 Community License Agreement
Jaavid Aktar Husain and Raj Dabre and Aswanth Kumar and Jay Gala and Thanmay Jayakumar and Ratish Puduppully and Anoop Kunchukuttan
Multilingual Language Model
N.A.
Open
Sector Agnostic
02/05/25 11:01:10
0
Activity Overview
1
94 
0 
1,215
Tags
- Multilingual
- LLaMA2
- Llama
- Instruction-Tuning
License Control
Llama 2 Community License Agreement
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
AI4Bharat- 400 M - RomanSetu Multilingual Native-to-Roman Model
RomanSetu is a multilingual continual pretrained transformer model designed for transliteration across six Indic languages
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.
NLP
Automatic Speech Recognition
Speech-to-Text
- 0
- 29
- 0
843
Updated 1 year(s) ago
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
Automatic Speech Recognition
NLP
- 0
- 35
- 0
- 845
Updated 1 year(s) ago
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
NLP
Automatic Speech Recognition
Kashmiri
Speech-to-Text
- 0
- 28
- 0
- 964
Updated 1 year(s) ago
AI4Bharat - Romansetu-200M -Multilingual LLM for Indian langauges using romanization
RomanSetu is Efficiently unlocking multilingual (Indian Languages) capabilities of Large Language Models via Romanization.
AI4Bharat - Romansetu-100M - Multilingual LLM for Indian langauges using romanization
RomanSetu is Efficiently unlocking multilingual (Indian Languages) capabilities of Large Language Models via Romanization.
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.
NLP
Automatic Speech Recognition
Audio Processing
- 0
- 25
- 0
- 962
Updated 1 year(s) ago
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.
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.
NLP
Large Model
high-quality-translation
low-resource-NLP
cross-lingual
Multilingual
Machine Translation
Transformer
- 0
- 35
- 0
- 1,110
Updated 1 year(s) ago
© 2026 - Copyright AIKosh. All rights reserved.