import sys
import gradio as gr
from transformers import AutoTokenizer
import torch


tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-en-ar")
model = torch.load("helsinki_fineTuned.pt", map_location=torch.device('cpu'))
model.eval()


def translate_gradio(input):
    tokenized_text = tokenizer.prepare_seq2seq_batch([input], return_tensors='pt')
    encode = model.generate(**tokenized_text)
    text_ar = tokenizer.batch_decode(encode,skip_special_tokens=True)[0]
    return text_ar
translate_interface = gr.Interface(fn = translate_gradio,
                                   allow_flagging = True,
                                 
                                   title = 'Translating "English Data Science" content into Arabic',
                                   inputs=gr.inputs.Textbox(lines = 7, label = 'english content'),
                                   outputs="text",
                                   examples = [['In the last few years the RNN-based architectures have shown the best performance in machine translation problems, but still they have some problems that had to be solved. First, they have a difficulty to cope with long-range dependencies (also LSTM when it has to deal with really long sentences). Secondly, each hidden state depends on the previous one which impossible to parallelize and makes it inefficient on GPUs.']]
                                                               )
translate_interface.launch(inline = False)