app.py

"""import gradio as gr
import nltk
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

nltk.download('punkt')

def fragment_text(text, tokenizer):
    sentences = nltk.tokenize.sent_tokenize(text)
    max_len = tokenizer.max_len_single_sentence

    chunks = []
    chunk = ""
    count = -1

    for sentence in sentences:
        count += 1
        combined_length = len(tokenizer.tokenize(sentence)) + len(chunk)

        if combined_length <= max_len:
            chunk += sentence + " "
        else:
            chunks.append(chunk.strip())
            chunk = sentence + " "

    if chunk != "":
        chunks.append(chunk.strip())

    return chunks


def summarize_text(text, tokenizer, model):
    chunks = fragment_text(text, tokenizer)

    summaries = []
    for chunk in chunks:
        input = tokenizer(chunk, return_tensors='pt')
        output = model.generate(**input)
        summary = tokenizer.decode(*output, skip_special_tokens=True)
        summaries.append(summary)

    final_summary = " ".join(summaries)
    return final_summary

# Load pre-trained model and tokenizer
checkpoint = "tclopess/bart_samsum"
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
model = AutoModelForSeq2SeqLM.from_pretrained(checkpoint)

# Define Gradio Interface
iface = gr.Interface(
    fn=summarize_text,
    inputs=gr.Textbox(),
    outputs=gr.Textbox(),
    live=True
)

# Launch the Gradio Interface
iface.launch()


import gradio as gr
import nltk
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

nltk.download('punkt')

def fragment_text(text, tokenizer):
    sentences = nltk.tokenize.sent_tokenize(text)
    max_len = tokenizer.max_len_single_sentence

    chunks = []
    chunk = ""
    count = -1

    for sentence in sentences:
        count += 1
        combined_length = len(tokenizer.tokenize(sentence)) + len(chunk)

        if combined_length <= max_len:
            chunk += sentence + " "
        else:
            chunks.append(chunk.strip())
            chunk = sentence + " "

    if chunk != "":
        chunks.append(chunk.strip())

    return chunks


def summarize_text(text, tokenizer, model):
    chunks = fragment_text(text, tokenizer)

    summaries = []
    for chunk in chunks:
        input = tokenizer(chunk, return_tensors='pt')
        output = model.generate(**input)
        summary = tokenizer.decode(*output, skip_special_tokens=True)
        summaries.append(summary)

    final_summary = " ".join(summaries)
    return final_summary

checkpoint = "tclopess/bart_samsum"
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
model = AutoModelForSeq2SeqLM.from_pretrained(checkpoint)

def summarize_and_display(text):
    summary = summarize_text(text, tokenizer, model)
    return summary

iface = gr.Interface(
    fn=summarize_and_display,
    inputs=gr.Textbox(label="Enter text to summarize:"),
    outputs=gr.Textbox(label="Summary:"),
    live=True,
    title="Text Summarizer with Button",
    description="Click the 'Summarize' button to generate a summary of the text.",
)

iface.launch(share=True)
""""

import gradio as gr
import nltk
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

nltk.download('punkt')

def fragment_text(text, tokenizer):
    sentences = nltk.tokenize.sent_tokenize(text)
    max_len = tokenizer.max_len_single_sentence

    chunks = []
    chunk = ""
    count = -1

    for sentence in sentences:
        count += 1
        combined_length = len(tokenizer.tokenize(sentence)) + len(chunk)

        if combined_length <= max_len:
            chunk += sentence + " "
        else:
            chunks.append(chunk.strip())
            chunk = sentence + " "

    if chunk != "":
        chunks.append(chunk.strip())

    return chunks


def summarize_text(text, tokenizer, model):
    chunks = fragment_text(text, tokenizer)

    summaries = []
    for chunk in chunks:
        input = tokenizer(chunk, return_tensors='pt')
        output = model.generate(**input)
        summary = tokenizer.decode(*output, skip_special_tokens=True)
        summaries.append(summary)

    final_summary = " ".join(summaries)
    return final_summary

checkpoint = "tclopess/bart_samsum"
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
model = AutoModelForSeq2SeqLM.from_pretrained(checkpoint)

def summarize_and_display(text):
    summary = summarize_text(text, tokenizer, model)
    return summary

iface = gr.Interface(
    fn=summarize_and_display,
    inputs=gr.Textbox(label="Enter text to summarize:"),
    outputs=gr.Textbox(label="Summary:"),
    live=False,  # Set live to False to add a button
    button="Summarize",  # Add a button with the label "Summarize"
    title="Text Summarizer with Button",
)

iface.launch(share=True)