---
license: mit
language:
- en
- ne
- sa
base_model:
- ai4bharat/indictrans2-indic-en-1B
---

# IndicTrans2 Sanskrit ↔ Nepali (LoRA Fine-tuned)

[![HF Model Hub](https://img.shields.io/badge/Hugging%20Face-Model%20Hub-blue)](https://huggingface.co/karki-dennish/indictrans2-sanNpi)

This repository provides a [LoRA](https://arxiv.org/abs/2106.09685)-based fine-tuning of the [IndicTrans2](https://huggingface.co/ai4bharat/indictrans2-indic-indic-dist-320M) model for translation between Sanskrit and Nepali (both in Devanagari script).

---

## Model Details

- **Base Model**: [ai4bharat/indictrans2-indic-indic-dist-320M](https://huggingface.co/ai4bharat/indictrans2-indic-indic-dist-320M)  
- **Fine-tuning Approach**: [LoRA (Low-Rank Adaptation)](https://arxiv.org/abs/2106.09685)  
- **Language Pair**:  
  - Source: Sanskrit (`san_Deva`)  
  - Target: Nepali (`npi_Deva`)

> **Note**: In the training script, the source and target might be reversed (`npi_Deva` → `san_Deva`). However, in the example usage code below, we demonstrate translating from Sanskrit to Nepali. Adjust `src_lang` and `tgt_lang` as needed for your specific use case.

---

## Intended Use

- **Primary Use**: Machine translation from Sanskrit to Nepali (and vice versa if you reverse the language codes).
- **Domains**: General domain, though performance may vary depending on your dataset and domain specifics.

---

## How to Use

Below is a minimal code snippet demonstrating how to use this LoRA-finetuned model for translation. The snippet uses:

- [Transformers](https://github.com/huggingface/transformers) library for the model and tokenizer  
- [IndicTransToolkit](https://github.com/VarunGumma/IndicTransToolkit) for preprocessing and postprocessing Indic text  

### Installation

**Install Transformers** (if not already installed):
   ```bash
    pip install transformers
    git clone https://github.com/VarunGumma/IndicTransToolkit
    cd IndicTransToolkit
    pip install --editable ./
    pip install torch
    pip install ipython jupyter
    
    import torch
    from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
    from IndicTransToolkit import IndicProcessor
  ```

### Inference Example
  ```bash
    ip = IndicProcessor(inference=True)
    model_name = "karki-dennish/indictrans2-sanNpi"  # or your Hugging Face repo ID
    
    tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
    model = AutoModelForSeq2SeqLM.from_pretrained(model_name, trust_remote_code=True)
    
    def translate_san_to_npi(texts):
        # 1. Preprocess
        batch = ip.preprocess_batch(texts, src_lang="san_Deva", tgt_lang="npi_Deva")
        encoded = tokenizer(batch, padding=True, truncation=True, return_tensors="pt")
  
        # 2. Generate translations
        with torch.inference_mode():
            outputs = model.generate(**encoded, num_beams=5, max_length=256)
    
        # 3. Decode and Postprocess
        translations = tokenizer.batch_decode(outputs, skip_special_tokens=True)
        translations = ip.postprocess_batch(translations, lang="npi_Deva")
    
        return translations
  
    # Example usage
    sanskrit_sentences = [
        "अहं गच्छामि।",  # "I am going."
        "किं समाचारः?"    # "What news?"
    ]
    
    translated = translate_san_to_npi(sanskrit_sentences)
    for s, t in zip(sanskrit_sentences, translated):
        print(f"Sanskrit: {s} --> Nepali: {t}")
  ```

### Citation

  ```bibtex
  @misc{indictrans2-lora-san-npi,
    title         = {IndicTrans2 Sanskrit-Nepali LoRA Fine-tuned Model},
    author        = {Dennish Karki},
    howpublished  = {Hugging Face repository},
    year          = {2025},
    url           = {https://huggingface.co/karki-dennish/indictrans2-sanNpi}
  }