Romaneng2nep V3

🚀 romaneng2nep_v2

This model is a fine - tuned version of google/mt5-small on the syubraj/roman2nepali-transliteration dataset, aiming to achieve high - quality Romanized English to Nepali translation.

🚀 Quick Start

This model is a fine-tuned version of google/mt5-small on an syubraj/roman2nepali-transliteration. It achieves the following results on the evaluation set:

• Loss: 2.9652
• Gen Len: 5.1538

✨ Features

• Based on the fine - tuned google/mt5-small model.
• Trained on the syubraj/roman2nepali-transliteration dataset.
• Achieved specific loss and generation length results on the evaluation set.

📦 Installation

!pip install transformers

💻 Usage Examples

Basic Usage

from transformers import AutoTokenizer, MT5ForConditionalGeneration

checkpoint = "syubraj/romaneng2nep_v3"
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
model = MT5ForConditionalGeneration.from_pretrained(checkpoint)

# Set max sequence length
max_seq_len = 20

def translate(text):
    # Tokenize the input text with a max length of 20
    inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=max_seq_len)

    # Generate translation
    translated = model.generate(**inputs)

    # Decode the translated tokens back to text
    translated_text = tokenizer.decode(translated[0], skip_special_tokens=True)
    return translated_text

# Example usage
source_text = "muskuraudai"  # Example Romanized Nepali text
translated_text = translate(source_text)
print(f"Translated Text: {translated_text}")

📚 Documentation

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

Training results

Framework versions

Citation

If you find this model useful, please cite the work.

@misc {yubraj_sigdel_2024,
	author       = { {Yubraj Sigdel} },
	title        = { romaneng2nep_v3 (Revision dca017e) },
	year         = 2024,
	url          = { https://huggingface.co/syubraj/romaneng2nep_v3 },
	doi          = { 10.57967/hf/3252 },
	publisher    = { Hugging Face }
}

📄 License

This model is licensed under the apache - 2.0 license.