| --- |
| library_name: transformers |
| tags: |
| - cryptology |
| - cipher |
| datasets: |
| - asimokby/Turkish-OSCAR-GEC |
| language: |
| - tr |
| base_model: |
| - google-t5/t5-base |
| license: apache-2.0 |
| --- |
| |
| This project contains a text-to-text model designed to decrypt Turkish text encoded using a substitution cipher. |
| In a substitution cipher, each letter in the plaintext is replaced by a corresponding, unique letter to form the ciphertext. |
| The model leverages statistical and linguistic properties of Turkish to make educated guesses about the letter substitutions, |
| aiming to recover the original plaintext message. |
|
|
| This model is for monoalphabetic Turkish substitution ciphers and it outputs decoded text. |
|
|
| Example: |
|
|
| Encoded text: |
| **Wn cqwqp fqpöqgbatqj ckjxq çmxmçmvy rafhqça zgqjgaçkxnh.** |
|
|
| Decoded text: |
| **Bu sabah kahvaltıdan sonra yürüyüşe çıkmayı planlıyorum.** |
|
|
| Suggested Usage: |
| ```py |
| #Load the model and tokenizer |
| cipher_text = "" #Encoded text here! |
| inputs = tokenizer(cipher_text, return_tensors="pt", padding=True, truncation=True, max_length=256).to(device) |
| outputs = model.generate(inputs["input_ids"], max_length=256) |
| decoded_text = tokenizer.decode(outputs[0], skip_special_tokens=True) |
| ``` |
