app.py

#%%
import gradio as gr
from dotenv import load_dotenv

from translate import run_translate
from diacritize import diacritize, diacritize_if_not_already
from translit import taatik, translit
from semsearch import update_df
from tts import get_audio
from consts import CSS, ABOUT, JS_FUNC
load_dotenv()

with gr.Blocks(title = "Levanti - Levantine Arabic Translation Tools",
               css=CSS,
               theme="default") as demo:
    # gr.HTML("<h2><span style='color: #2563eb'>Levantine Arabic</span> Translator</h2>")
    gr.HTML("<h2><span><span style='color: #2563eb'>Levanti</span>ne Translator</span></h2>Levantine Arabic Translation Tools")
    with gr.Tab('Translation', elem_id="tab1"):
        with gr.Row():
            with gr.Column():
                input_text = gr.Textbox(label="Input",
                                        info = "Colloquial Arabic or English",
                                        placeholder="Enter text in Arabic or English",
                                        lines=2,
                                        elem_id="input")

                gr.Examples(["I called him two times, he's not picking up", "خلينا ندور على مطعم تاني"],
                            input_text,
                            label="Examples")

                btn = gr.Button("Translation")
                with gr.Row():
                    dialect = gr.Radio(["Palestinian", "Syrian", "Lebanese", "Egyptian"],
                                        label = "Dialect",
                                        info="Affects translation to Arabic",
                                        value="Palestinian")

                # gr.Markdown("Built by [Guy Mor-Lan](mailto:[email protected]). Pronunciation model is specifically tailored to urban Palestinian Arabic. Text-to-speech uses Microsoft Azure's API and may provide different result from the transliterated pronunciation.")
                gr.Markdown("Create by [Guy Mor-Lan](mailto:[email protected]) as part of the [Levanti](https://huggingface.co/datasets/guymorlan/levanti) project. Audio is produced using Azure TTS with predicted diacritics and heuristics.", elem_id="footer")

            with gr.Column():
                with gr.Group(elem_id="grp"):
                        gr.HTML("Translation")
                        # gr.Markdown("תרגום", elem_id="diacritized")
                        translation_output = gr.HTML("<br>", visible=True, label="Translation", elem_id="main")

                hidden_arabic = gr.Textbox(lines=1, elem_id="trans", visible=False)

                diacritized_output = gr.Textbox(label="Diacritization (experimental)", lines=1, elem_id="diacritized",
                                                interactive=False)
                taatik_output = gr.Textbox(label="Transliteration (Experimental)", lines=1, elem_id="taatik",
                                           text_align="right", interactive=False)
                # diacritized_output = gr.HTML("<br>", label="ניקוד")
                # taatik_output = gr.HTML("<br>", label="תעתיק")

                audio = gr.Audio(label="Audio (Azure)", interactive=False,
                                 autoplay=True)
                audio_button = gr.Button("Generate Audio")
                audio_button.click(get_audio, inputs=[diacritized_output], outputs=[audio])


        btn.click(run_translate, inputs=[input_text, dialect],
                  outputs=[translation_output, hidden_arabic], api_name="en2ar",
                  js="function jump(x, y){document.getElementById('main').scrollIntoView(); return [x, y];}")

        input_text.submit(run_translate, inputs=[input_text, dialect],
                          outputs=[translation_output, hidden_arabic], scroll_to_output=True)
        hidden_arabic.change(diacritize, inputs=[hidden_arabic], outputs=[diacritized_output])
        diacritized_output.change(translit, inputs=[diacritized_output], outputs=[taatik_output])
        # with gr.Row():
        #     nearest_df = gr.DataFrame(headers=["ערבית", "עברית", "מאומת"], visible=False, wrap=True,
        #                               elem_id="nearest", label="תוצאות קרובות מתוך קורפוס Levanti", height=300)

        # hidden_arabic.change(update_df, inputs=[hidden_arabic], outputs=[nearest_df])
        
    with gr.Tab("Diacritization and Transliteration", elem_id="tab2"):
        with gr.Row():
            with gr.Column():
                diac_text = gr.Textbox(label="Input", placeholder="Insert text in Arabic", lines=1,
                                        info = "For transliteration only, insert diacritized text",
                                        elem_id="diac_input")
                gr.Examples(["خلينا ندور على مطعم تاني", "قَدِيْش حَقّ الْبَنْدُورَة؟"], diac_text, 
                            label="Examples", elem_id="diac_ex")
                btn2 = gr.Button("Send")
                
            with gr.Column():
                diacritized_output2 = gr.Textbox(label="Diacritization", lines=1,
                                                  elem_id="diacritized2")
                taatik_output2 = gr.Textbox(label="Transliteration", lines=1,
                                             elem_id="taatik2")

        # input_text.submit(run_translate, inputs=[input_text, dialect],
        #                   outputs=[translation_output], scroll_to_output=True)
        # hidden_arabic.change(diacritize, inputs=[hidden_arabic], outputs=[diacritized_output])
        # diacritized_output.change(taatik, inputs=[diacritized_output], outputs=[taatik_output])
        btn2.click(diacritize_if_not_already, inputs=[diac_text], outputs=[diacritized_output2])
        diac_text.submit(diacritize_if_not_already, inputs=[diac_text], outputs=[diacritized_output2])
        diacritized_output2.change(translit, inputs=[diacritized_output2], outputs=[taatik_output2])
    with gr.Tab("About", elem_id="tab3"):
        with gr.Row():
            gr.HTML("<h2>About</h2>")
            gr.Markdown(ABOUT, elem_id="about")



demo.launch(ssl_verify=False)