nirajan111/nepali-transliteration

Nepali Transliteration Model

Model Description

This model performs bidirectional transliteration between Nepali (Devanagari script) and English (Latin script). It can convert:

• —English text to Nepali Devanagari script
• —Nepali Devanagari text to English romanization

The model is fine-tuned for accurate transliteration of Nepali names, places, and common vocabulary.

Model Details

• —Model Type: Sequence-to-sequence text generation
• —Language(s): Nepali (ne), English (en)
• —License: Apache 2.0
• —Base Model: google/mt5-small
• —Training Data: Custom Nepali-English transliteration dataset
• —Training Steps: 34000]
• —Parameters: 400MB

Intended Use

Primary Use Cases

• —Converting English names and words to Nepali Devanagari script
• —Romanizing Nepali text for international audiences
• —Supporting multilingual applications and keyboards
• —Academic research in computational linguistics
• —Cultural preservation and digital humanities projects

Out-of-Scope Use Cases

• —Machine translation (this model only handles transliteration, not translation)
• —Text generation beyond transliteration
• —Processing languages other than Nepali and English

How to Use

Installation

pip install transformers torch

Basic Usage

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

# Load model and tokenizer
model_name = nirajan111/nepali-transliteration"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSeq2SeqLM.from_pretrained(model_name)

# English to Nepali
def transliterate_en_to_ne(text):
    inputs = tokenizer(f"en2ne: {text}", return_tensors="pt", max_length=128, truncation=True)
    outputs = model.generate(**inputs, max_length=128, num_beams=4, early_stopping=True)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

# Nepali to English
def transliterate_ne_to_en(text):
    inputs = tokenizer(f"ne2en: {text}", return_tensors="pt", max_length=128, truncation=True)
    outputs = model.generate(**inputs, max_length=128, num_beams=4, early_stopping=True)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

# Examples
print(transliterate_en_to_ne("namaste"))  # Expected: नमस्ते
print(transliterate_ne_to_en("काठमाडौं"))  # Expected: kathmandu

Advanced Usage

# Batch processing
texts = ["namaste", "dhanyabad", "kathmandu"]
inputs = tokenizer([f"en2ne: {text}" for text in texts], 
                  return_tensors="pt", padding=True, truncation=True)
outputs = model.generate(**inputs, max_length=128, num_beams=4)
results = tokenizer.batch_decode(outputs, skip_special_tokens=True)

Training Data

The model was trained on a custom dataset containing:

• —Size: [Update with dataset size, e.g., 50,000 transliteration pairs]
• —Sources:
• —Nepali names and places
• —Common vocabulary
• —Cultural terms
• —Government documents
• —Educational materials
• —Preprocessing: Text normalization, duplicate removal, quality filtering
• —Split: 80% training, 10% validation, 10% testing

Training Procedure

Training Hyperparameters

• —Batch Size: 64 (training), 16 (evaluation)
• —Learning Rate: 0.00005
• —Epochs: 10
• —Optimizer: AdamW
• —Weight Decay: 0.01
• —Warmup Steps: 500
• —Max Sequence Length: 128

Training Infrastructure

• —Hardware: kaggle A100
• —Framework: PyTorch, Transformers
• —Training Time: 12hr

Evaluation

Metrics

• —BLEU Score: 0.85
• —Word Accuracy: 0.92
• —Character Error Rate: 0.138
• —Exact Match: 0.78

Test Results

Limitations and Bias

Known Limitations

• —Performance may vary with proper nouns not seen during training
• —Limited handling of mixed-script text
• —May struggle with very long compound words
• —Accuracy depends on text quality and standardization

Potential Biases

• —Training data may over-represent certain regions or dialects of Nepali
• —Model may have better performance on formal/literary Nepali vs. colloquial forms
• —Potential bias toward more common transliteration patterns

Ethical Considerations

• —This model supports language preservation and digital inclusion for Nepali speakers
• —Care should be taken when using for official documents or names
• —Users should verify outputs for critical applications
• —The model should not be used to misrepresent or appropriate Nepali culture

Citation

@model{nepali-transliteration-2024,
  title={Nepali Transliteration Model},
  author={Nirajan Sah},
  year={2025},
  url={https://huggingface.co/nirajan1111/nepali-transliteration-model}
}

Model Card Contact

For questions or feedback about this model, please contact: [nirajansah1111@gmail.com]

Acknowledgments

• —Thanks to the Nepali language community for providing linguistic insights