inference.py

def evaluate(sentence):

    sentence = preprocess_sentence(sentence)

    inputs = [inp_lang.word_index[i] for i in sentence.split(' ')]
    inputs = tf.keras.preprocessing.sequence.pad_sequences([inputs],
                                                         maxlen=max_length_inp,
                                                         padding='post')
    inputs = tf.convert_to_tensor(inputs)

    result = ''

    hidden = [tf.zeros((1, units))]
    enc_out, enc_hidden = encoder(inputs, hidden)

    dec_hidden = enc_hidden
    dec_input = tf.expand_dims([targ_lang.word_index['<start>']], 0)

    for t in range(max_length_targ):
        predictions, dec_hidden = decoder(dec_input,dec_hidden,enc_out)

        print(predictions[0])
        predicted_id = tf.argmax(predictions[0]).numpy()
        print(predicted_id)

        result += targ_lang.index_word[predicted_id] + ' '

        if targ_lang.index_word[predicted_id] == '<end>':
            #return result, sentence, attention_plot
            return result, sentence

        # the predicted ID is fed back into the model
        dec_input = tf.expand_dims([predicted_id], 0)

  
    return result, sentence
  
  def translate(sentence):
    result, sentence = evaluate(sentence)
    print('Input: %s' % (sentence))
    print('Predicted translation: {}'.format(result))