opus-mt-synthetic-en-so

from transformers import MarianMTModel, MarianTokenizer

# Load the pre-trained model and tokenizer
model_name = "Helsinki-NLP/opus-mt-synthetic-en-so"
model = MarianMTModel.from_pretrained(model_name)
tokenizer = MarianTokenizer.from_pretrained(model_name)

# Example source text (English)
source_texts = ["Hello, how are you?", "Good morning!", "What is your name?"]

# Tokenize the input texts
inputs = tokenizer(source_texts, return_tensors="pt", padding=True, truncation=True)

# Generate translations
translated_ids = model.generate(inputs["input_ids"])

# Decode the generated tokens to get the translated text
translated_texts = tokenizer.batch_decode(translated_ids, skip_special_tokens=True)

# Print the translations
for src, tgt in zip(source_texts, translated_texts):
    print(f"Source: {src} => Translated: {tgt}")

from transformers import MarianMTModel, MarianTokenizer

# Load the pre-trained model and tokenizer
model_name = "Helsinki-NLP/opus-mt-synthetic-en-so"
model = MarianMTModel.from_pretrained(model_name)
tokenizer = MarianTokenizer.from_pretrained(model_name)

# Example source text (English)
source_texts = ["Hello, how are you?", "Good morning!", "What is your name?"]

# Tokenize the input texts
inputs = tokenizer(source_texts, return_tensors="pt", padding=True, truncation=True)

# Generate translations
translated_ids = model.generate(inputs["input_ids"])

# Decode the generated tokens to get the translated text
translated_texts = tokenizer.batch_decode(translated_ids, skip_special_tokens=True)

# Print the translations
for src, tgt in zip(source_texts, translated_texts):
    print(f"Source: {src} => Translated: {tgt}")

@article{degibert2025scaling,
  title={Scaling Low-Resource MT via Synthetic Data Generation with LLMs},
  author={de Gibert, Ona and Attieh, Joseph and Vahtola, Teemu and Aulamo, Mikko and Li, Zihao and V{\'a}zquez, Ra{\'u}l and Hu, Tiancheng and Tiedemann, J{\"o}rg},
  journal={arXiv preprint arXiv:2505.14423},
  year={2025}
}

@article{degibert2025scaling,
  title={Scaling Low-Resource MT via Synthetic Data Generation with LLMs},
  author={de Gibert, Ona and Attieh, Joseph and Vahtola, Teemu and Aulamo, Mikko and Li, Zihao and V{\'a}zquez, Ra{\'u}l and Hu, Tiancheng and Tiedemann, J{\"o}rg},
  journal={arXiv preprint arXiv:2505.14423},
  year={2025}
}