section7.ipynb

Kernel: Python 3

Introduction aux Blocks

Installez les bibliothèques 🤗 Transformers et 🤗 Gradio pour exécuter ce notebook.

!pip install datasets transformers[sentencepiece]
!pip install gradio

import gradio as gr

def flip_text(x):
    return x[::-1]


demo = gr.Blocks()

with demo:
    gr.Markdown(
        """
        # Inverser le texte !
        Commencer à taper ci-dessous pour voir le résultat.
        """
    )
    input = gr.Textbox(placeholder="Inverser ce texte")
    output = gr.Textbox()

    input.change(fn=flip_text, inputs=input, outputs=output)

demo.launch()

import numpy as np
import gradio as gr

demo = gr.Blocks()


def flip_text(x):
    return x[::-1]


def flip_image(x):
    return np.fliplr(x)


with demo:
    gr.Markdown("Inverser des fichiers texte ou image à l'aide de cette démo.")
    with gr.Tabs():
        with gr.TabItem("Inverser le texte"):
            with gr.Row():
                text_input = gr.Textbox()
                text_output = gr.Textbox()
            text_button = gr.Button("Inverser")
        with gr.TabItem("Inverser l'image"):
            with gr.Row():
                image_input = gr.Image()
                image_output = gr.Image()
            image_button = gr.Button("Inverser")

    text_button.click(flip_text, inputs=text_input, outputs=text_output)
    image_button.click(flip_image, inputs=image_input, outputs=image_output)

demo.launch()

import gradio as gr

api = gr.Interface.load("huggingface/asi/gpt-fr-cased-small")


def complete_with_gpt(text):
    # Utilisez les 50 derniers caractères du texte comme contexte.
    return text[:-50] + api(text[-50:])


with gr.Blocks() as demo:
    textbox = gr.Textbox(placeholder="Tapez ici et appuyez sur la touche Entrée...", lines=4)
    btn = gr.Button("Générer")

    btn.click(complete_with_gpt, textbox, textbox)

demo.launch()

from transformers import pipeline

import gradio as gr

asr = pipeline("automatic-speech-recognition", "wav2vec2-large-xlsr-53-french")
classifier = pipeline("text-classification", model="tblard/tf-allocine")


def speech_to_text(speech):
    text = asr(speech)["text"]
    return text


def text_to_sentiment(text):
    return classifier(text)[0]["label"]


demo = gr.Blocks()

with demo:
    audio_file = gr.Audio(type="filepath")
    text = gr.Textbox()
    label = gr.Label()

    b1 = gr.Button("Reconnaître la parole")
    b2 = gr.Button("Classifier le sentiment")

    b1.click(speech_to_text, inputs=audio_file, outputs=text)
    b2.click(text_to_sentiment, inputs=text, outputs=label)

demo.launch()

import gradio as gr


def change_textbox(choice):
    if choice == "court":
        return gr.Textbox.update(lines=2, visible=True)
    elif choice == "long":
        return gr.Textbox.update(lines=8, visible=True)
    else:
        return gr.Textbox.update(visible=False)


with gr.Blocks() as block:
    radio = gr.Radio(
        ["court", "long", "none"], label="Quel genre d'essai souhaitez-vous écrire ?"
    )
    text = gr.Textbox(lines=2, interactive=True)

    radio.change(fn=change_textbox, inputs=radio, outputs=text)
    block.launch()