ctranslate2_mwe.py

import ctranslate2


# Replace with your tokenize function and source tokenization model
def tokenize(input_sentences):
    tokens = [input_sentence.split(" ") for input_sentence in input_sentences]
    return tokens

# Replace with your detokenize function and target tokenization model
def detokenize(outputs):
    translation = [" ".join([t for t in output]) for output in outputs]
    return translation


# Modify the path to the CTranslate2 model directory
model_path = "ctranslate2_model"

source_sentences = ["how are you?", "fine, thanks!", "everything is great.", "I am happy to know that."]

translator = ctranslate2.Translator(model_path, "cpu") # "cpu" or "cuda"

outputs = translator.translate_batch(tokenize(source_sentences), beam_size=5)
translations = detokenize([output.hypotheses[0] for output in outputs])
print(*translations, sep="\n")