pib-indic-en-v1 is a LoRA adapter fine-tuned on AI4Bharat's IndicTrans2 (ai4bharat/indictrans2-indic-en-dist-200M) for Hindi-to-English translation. It is an Indic translation model for offline/air-gapped use: the adapter and base model run fully on-premise, with no external API calls required at inference time.
The IndicTrans2 base model supports translation across the 22 scheduled Indian languages (base-model capability; Nife has fine-tuned and validated this adapter for Hindi-English only).
Machine translation from Hindi into English, tuned for formal/administrative text. Intended to be loaded as a LoRA adapter on top of the IndicTrans2 dist-200M base using the PEFT library, and runs in fully offline or air-gapped environments.
This adapter inherits the limitations of the IndicTrans2 base model. Fine-tuning targeted Hindi-English translation of formal/administrative text; quality outside that pair and domain may be lower. Outputs should be reviewed by a human translator where accuracy matters.
Validate translation quality on your own data before production use. Use human review for any publishable or decision-driving output.
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
from peft import PeftModel
base = "ai4bharat/indictrans2-indic-en-dist-200M"
tokenizer = AutoTokenizer.from_pretrained(base, trust_remote_code=True)
model = AutoModelForSeq2SeqLM.from_pretrained(base, trust_remote_code=True)
model = PeftModel.from_pretrained(model, "NifeLab/pib-indic-en-v1")
# Pre/post-processing with AI4Bharat's IndicTransToolkit is recommended,
# as with the base IndicTrans2 models.
Fine-tuned on publicly available PIB releases and other public government websites, together with the public Samanantar corpus from AI4Bharat (CC0). Only public sources were used; no proprietary or confidential data is included.
Parameter-efficient fine-tuning (LoRA) of ai4bharat/indictrans2-indic-en-dist-200M.
No formal benchmark evaluation has been published for this adapter yet. Users should evaluate on their own data before relying on it.
If you use this model, please cite the IndicTrans2 base work:
@article{gala2023indictrans,
title={IndicTrans2: Towards High-Quality and Accessible Machine Translation Models for all 22 Scheduled Indian Languages},
author={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},
journal={Transactions on Machine Learning Research},
issn={2835-8856},
year={2023},
url={https://openreview.net/forum?id=vfT4YuzAYA}
}
ai4bharat/indictrans2-indic-en-dist-200M