MarianMT-english-urdu

This model is a fine-tuned version of Helsinki-NLP/opus-mt-en-ur on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.8389
• Model Preparation Time: 0.0054
• Bleu: 14.8710

Model description

More information needed

from transformers import pipeline

# Load fine-tuned model
model_checkpoint = "azherali/MarianMT-english-urdu"

# Create translation pipeline
translator = pipeline(
    "translation",
    model=model_checkpoint,
    tokenizer=model_checkpoint,
    src_lang="en_XX",
    tgt_lang="ur_PK"
)

# Run example translation
sentence = "I am very happy today."
result = translator(sentence)

print("Input:", sentence)
print("Translation:", result[0]['translation_text'])

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Framework versions

• Transformers 4.55.2
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.21.4