Government Of India
A-
A
A+
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.
1 
94 
214.60 KB 
2,727
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
Indic Trans2
Metadata
MIT
AI4Bharat
Machine Translation Model
Other
Open
Sector Agnostic
06/07/26 16:12:22
214.60 KB
Tags
- Machine Translation
- Computational Linguistics
- Language Modeling
- Bilingual Translation
- Multilingual Translation
- Machine Translation
- Regional Languages
- Indian Languages
- Indic-TransV2
- NLP
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
SPRING-INX-DATA2VEC-AQC-GUJARATI
Automatic Speech Recognition (ASR) model for speech recognition, processing audio and transcribing spoken content into text.The inference code, installation requirements, and usage instructions are available in the SPRING Lab, IIT Madras GitHub repository: https://github.com/Speech-Lab-IITM/Fairseq-Inference
ssl
Low-resource languages
SSL_finetunning
Data2vec_aqc
spring_lab
IITM
gujarati
- 0
- 2
- 3.52 GB
- 31
Updated 24 day(s) ago
SPRING-INX-DATA2VEC-AQC-HINDI
Automatic Speech Recognition (ASR) model for speech recognition, processing audio and transcribing spoken content into text.The inference code, installation requirements, and usage instructions are available in the SPRING Lab, IIT Madras GitHub repository: https://github.com/Speech-Lab-IITM/Fairseq-Inference
Low-resource languages
ssl
IITM
spring_lab
Data2vec_aqc
SSL_finetunning
hindi
- 0
- 0
- 3.53 GB
- 27
Updated 24 day(s) ago
SPRING-INX-DATA2VEC-AQC-MANIPURI
Automatic Speech Recognition (ASR) model for speech recognition, processing audio and transcribing spoken content into text.The inference code, installation requirements, and usage instructions are available in the SPRING Lab, IIT Madras GitHub repository: https://github.com/Speech-Lab-IITM/Fairseq-Inference
Manipuri
Low Resource Languages
SSL_finetunning
Data2vec_aqc
spring_lab
IITM
ssl
- 0
- 1
- 3.52 GB
- 22
Updated 24 day(s) ago
SPRING-INX-DATA2VEC-AQC-ASSAMESE
Automatic Speech Recognition (ASR) model for speech recognition, processing audio and transcribing spoken content into text.The inference code, installation requirements, and usage instructions are available in the SPRING Lab, IIT Madras GitHub repository: https://github.com/Speech-Lab-IITM/Fairseq-Inference
SSL_finetunning
Assamese
ssl
IITM
spring_lab
Data2vec_aqc
Low-resource languages
- 0
- 1
- 3.52 GB
- 16
Updated 24 day(s) ago
IndicXlit
A Transformer-based multilingual transliteration model
NLP
Language Modeling
Multilingual Translation
Machine Translation
Regional Languages
Indian Languages
transliteration
- 0
- 54
- 3.94 MB
- 1,332
Updated 1 month(s) ago
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.
Indian Languages
Computational Linguistics
NLP
Indic-TransV2
Regional Languages
Machine Translation
Multilingual Translation
Bilingual Translation
Language Modeling
Machine Translation
- 1
- 94
- 214.60 KB
- 2,728
Updated 1 month(s) ago
Bhashini - Fastspeech2 Model using (HS)
Text-to-speech models trained using FastPitch and HiFi-GAN vocoder, separately for each language. Supports both 'female' and 'male' voices.
Transformer
Text to Speech
Language Detection
Multilingual
NLP
Text Processing
- 0
- 111
- 286.72 MB
- 2,095
Updated 1 month(s) ago
Bhashini - IndicNER
IndicNER is a multilingual Named Entity Recognition model fine-tuned on 11 Indian languages to identify named entities in text
NLP
Foreigners
Multilingual
Transformer
Token Classification
Pytorch
Samanantar
Bert
NER
- 2
- 176
- 591.28 MB
- 2,914
Updated 1 month(s) ago
Bhashini-AI4Bharat Textual Language Detection v1.0
Detect language from provided text, Currently supports 23 languages (English, Bangla, Manipuri, Bodo, Konkani, Oriya, Nepali, Marathi, Sindhi, Sanskrit, Malayalam, Urdu, Assamese, Telugu, Dogri, Gujarati, Kashmiri, Punjabi, Santali, Maithili, Hindi, Tamil, Kannada)
NLP
Text Processing
Deep Learning
Transformer
Text Language Detection
Multilingual
AI4Bharat
Bhashini
- 5
- 289
- 3 MB
- 5,522
Updated 1 month(s) ago
SPRING-INX-DATA2VEC-AQC-SANSKRIT
Automatic Speech Recognition (ASR) model for speech recognition, processing audio and transcribing spoken content into text.
The inference code, installation requirements, and usage instructions are available in the SPRING Lab, IIT Madras GitHub repository: https://github.com/Speech-Lab-IITM/Fairseq-Inference
low-resource-language
SSL_finetunning
Data2vec_aqc
spring_lab
IITM
ssl
Sanskrit
- 0
- 5
- 3.52 GB
- 220
Updated 1 month(s) ago
© 2026 - Copyright AIKosh. All rights reserved.