Translation Fine-Tuned Model (English β†’ Turkish)

This model is a fine-tuned version of 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:

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) 7.61
Fine-Tuned Model (this one) 29.93
Downloads last month
9
Safetensors
Model size
74.9M params
Tensor type
F32
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for LuigiJoseph/English-to-Turkish-ft

Finetuned
(1)
this model