CTranslate2 MWE

CTranslate2-mwe.py

import ctranslate2

def detokenize(result):
    translation = " ".join([t for t in result])
    return translation


def tokenize(input_sentence):
    tokens = input_sentence.split(" ")
    return tokens


# Change these variables
model_path = "fren_ctranslate2/"
my_sent = "ce qui a creusé les inégalités préexistantes"
prefix = "this has deepended"


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

original_result = translator.translate_batch([tokenize(my_sent)], beam_size=5)
translation = detokenize(original_result[0][0]["tokens"])
print(translation)

results = translator.translate_batch(
    [tokenize(my_sent)],
    target_prefix=[tokenize(prefix)],
    num_hypotheses=10,
    return_alternatives=True,
    beam_size=5)
for hypothesis in results[0]:
    print(detokenize(hypothesis["tokens"]))