Government Of India
A-
A
A+
ORGANISATION 
Upvote 3
Indic Trans2
AI4Bharat's Indic-Trans-v2 is a multilingual Transformer (~1.1BM) NMT model trained on Samanantar v2 dataset which is the largest publicly available parallel corpora collection for languages of India at the time of writing (23 March 2023). We currently release two models - Indic to English and English to Indic and support all the 22 scheduled languages of India.
- 3upvotes
104downloads
3,652views
0
0Shares
updated 06 Jul 2026
Upvote 3
LICENSE MIT
SECTOR Sector Agnostic
Model Card
Run Model
About Model
Bhashini - IndicTrans2 is the first open-source transformer-based multilingual NMT model that supports high-quality translations across all the 22 scheduled Indic languages — including multiple scripts for low-resouce languages like Kashmiri, Manipuri and Sindhi. It adopts script unification wherever feasible to leverage transfer learning by lexical sharing between languages. Overall, the model supports five scripts Perso-Arabic (Kashmiri, Sindhi, Urdu), Ol Chiki (Santali), Meitei (Manipuri), Latin (English), and Devanagari (used for all the remaining languages).
We open-souce all our training dataset (BPCC), back-translation data (BPCC-BT), final IndicTrans2 models, evaluation benchmarks (IN22, which includes IN22-Gen and IN22-Conv) and training and inference scripts for easier use and adoption within the research community. We hope that this will foster even more research in low-resource Indic languages, leading to further improvements in the quality of low-resource translation through contributions from the research community.
This code repository contains instructions for downloading the artifacts associated with IndicTrans2, as well as the code for training/fine-tuning the multilingual NMT models.
For more details about the use of model, refer to github: https://github.com/AI4Bharat/IndicTrans2/tree/main
Metadata
MIT
Sector Agnostic
AI4Bharat
N.A.
N.A.
N.A.
N.A.
N.A.
N.A.
N.A.
N.A.
Open
06/07/26 16:12:22
N.A.
214.60 KB
Tags
- Machine Translation
- Language Modeling
- Bilingual Translation
- Multilingual Translation
- Machine Translation
- Regional Languages
- Indian Languages
- Indic-TransV2
- NLP
- Computational Linguistics
IndicTrans2-main ( 20 files, 5 directories )
baseline_eval
5 files
huggingface_interface
10 files
.gitignore
2.12 KB
apply_sentence_piece.sh
1.65 KB
compute_comet_score.sh
3.45 KB
compute_metrics_significance.sh
3.14 KB
compute_metrics.sh
1.30 KB
eval_rev.sh
2.10 KB
eval.sh
2.03 KB
finetune.sh
1.47 KB
This preview shows 10 out of 25 items. Load more
License Control
MIT
Version Control
Version 1(214.60 KB)
- admin·1 year(s) ago
- chevron_right
IndicTrans2-main
- chevron_right
baseline_eval
- chevron_right
huggingface_interface
.gitignore
apply_sentence_piece.sh
compute_comet_score.sh
compute_metrics_significance.sh
compute_metrics.sh
eval_rev.sh
eval.sh
finetune.sh
- more_horiz 15 more
More Models from Digital India BHASHINI Division
Indic-Conformer model for ASR
Indo-Aryan Indic-Conformer is a multilingual speech model for North-Indian languages. This model is based on Conformer large architecture, with 115M parameters.
Joel-Speech-TTS
A Text-to-Speech (TTS) model developed for the Mizo language that converts written Mizo text into natural-sounding speech, supporting the development of Mizo-language voice applications and accessibility solutions.
mizo-f5-tts-v1
A Text-to-Speech (TTS) model developed for the Mizo language that converts written Mizo text into natural-sounding speech, supporting the development of Mizo-language voice applications and accessibility solutions.
MIZO MT
This Machine Translation (MT) model translates text from one language to another using a trained neural network. It can support multilingual communication and language translation applications. Translation quality depends on language coverage, training data, and contextual accuracy. For Mizo, evaluate the model using representative test sentences before deployment.
IITG-TTS-v1
The TTS was built using 5.18 hours of Mizo speech data. The Mizo text-to-speech (TTS) synthesis system built using the Variational Inference with Adversarial Learning for Text-to-Speech (VITS) framework.
IITG-Mizo-ASR-v1
A mizo ASR model.
IITG-Mizo-MT-v1
A Machine Translation model for English-Mizo
COILD Multilingual Translation
COILD Multilingual Translation Model (COILD-Mul-MT)
Mizomade-Mizo-EN-NLLB-S1
Fine-tuned pre trained model for Mizo-English machine translation, trained on Mizo-English parallel datasets to improve translation performance for the Mizo language.
BHASHINI IISc Sourashtra VITS TTS Models
VITS text-to-speech models for Sourashtra, a low-resource Indo-Aryan language. There are male and female voices, and each voice accepts text in either Tamil script or Sourashtra script.
© 2026 - Copyright AIKosh. All rights reserved.