metadata
library_name: transformers
language:
- en
- ur
metrics:
- bleu
# Fine-tuned mBART Model for English to Urdu Translation
This repository contains a fine-tuned mBART model for English to Urdu translation. The model has been trained on a custom dataset and evaluated on test data.
## Model Information
- **Model Name:** `abdulwaheed63/mbart_en_ur_finetuned`
- **Base Model:** `facebook/mbart-large-50`
- **Tokenizer:** `facebook/mbart-large-50`
- **Source Language:** English (`en`)
- **Target Language:** Urdu (`ur`)
## Usage
```python
from transformers import MBart50TokenizerFast, MBartForConditionalGeneration
# Load the fine-tuned model
model_name = "abdulwaheed63/mbart_en_ur_finetuned"
tokenizer = MBart50TokenizerFast.from_pretrained(model_name, src_lang="en_XX", tgt_lang="ur_PK")
model = MBartForConditionalGeneration.from_pretrained(model_name)
Evaluation
The model has been evaluated on a test dataset, and the following metrics were obtained:
- BLEU Score: 35.87
- Generation Length: 42.56
- Meteor Score: 0.60
Training Details
The model was trained using the transformers library with the following configuration:
- Training Loss: 1.5697
- Validation Loss: 1.1256
Dataset
The model was fine-tuned on a custom English-Urdu translation dataset. If you wish to use the same dataset, you can find the preprocessing script and dataset files in the data directory.
Acknowledgments
The fine-tuning process and code were inspired by the Hugging Face Transformers library.