---
language:
- en
- tr
metrics:
- bleu
base_model:
- ckartal/english-to-turkish-finetuned-model
pipeline_tag: translation
tags:
- transformers
- translation
---


# Translation Fine-Tuned Model (English → Turkish)

This model is a fine-tuned version of [ckartal/english-to-turkish-finetuned-model](https://huggingface.co/ckartal/english-to-turkish-finetuned-model) on a custom dataset for e-commerce shopping items.

## Model Details
- **Source language:** English (`en`)
- **Target language:** Turkish (`tr`)
- **Fine-tuned on:** Custom dataset for e-commerce translations
- **Base model:** ckartal/english-to-turkish-finetuned-model

## How to Use

You can use this model with the `transformers` library:

```python
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model_name = "LuigiJoseph/English-to-Turkish-ft"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSeq2SeqLM.from_pretrained(model_name)

text = "Hello, World!"
inputs = tokenizer.encode(text, return_tensors="pt")
outputs = model.generate(inputs)
translation = tokenizer.decode(outputs[0], skip_special_tokens=True)

print(translation)  # English translations
```

# **Evaluation Metrics**
The performance of the base model and the fine-tuned model was measured using the **BLEU** metric:

| Model | BLEU Score |
|--------|-----------|
| **Base Model** ([ckartal/english-to-turkish-finetuned-model](https://huggingface.co/ckartal/english-to-turkish-finetuned-model)) | **7.61** |
| **Fine-Tuned Model (this one)** | **29.93** |