Spaces:
Sleeping
Sleeping
Create test.py
Browse files
test.py
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# import gradio as gr
|
| 2 |
+
# from transformers import pipeline
|
| 3 |
+
# import os
|
| 4 |
+
# import pandas as pd
|
| 5 |
+
|
| 6 |
+
# # Load the text summarization pipeline
|
| 7 |
+
# summarizer = pipeline("summarization", model="astro21/bart-cls")
|
| 8 |
+
|
| 9 |
+
# chunk_counter = 0
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
# def summarize_text(input_text):
|
| 13 |
+
# global chunk_counter
|
| 14 |
+
# chunk_counter = 0
|
| 15 |
+
|
| 16 |
+
# max_chunk_size = 1024
|
| 17 |
+
# chunks = [input_text[i:i + max_chunk_size] for i in range(0, len(input_text), max_chunk_size)]
|
| 18 |
+
|
| 19 |
+
# summarized_chunks = []
|
| 20 |
+
# chunk_lengths = []
|
| 21 |
+
# summarized_chunks_only = []
|
| 22 |
+
|
| 23 |
+
# for chunk in chunks:
|
| 24 |
+
# chunk_counter += 1
|
| 25 |
+
# summarized_chunk = summarizer(chunk, max_length=128, min_length=64, do_sample=False)[0]['summary_text']
|
| 26 |
+
# summarized_chunks.append(f"Chunk {chunk_counter}:\n{summarized_chunk}")
|
| 27 |
+
# summarized_chunks_only.append(summarized_chunk)
|
| 28 |
+
|
| 29 |
+
# chunk_lengths.append(len(chunk))
|
| 30 |
+
|
| 31 |
+
# summarized_text = "\n".join(summarized_chunks)
|
| 32 |
+
# summarized_text_only = "\n".join(summarized_chunks_only)
|
| 33 |
+
|
| 34 |
+
# # Save the merged summary to a file
|
| 35 |
+
# with open("summarized.txt", "w") as output_file:
|
| 36 |
+
# output_file.write(summarized_text_only)
|
| 37 |
+
|
| 38 |
+
# chunk_df = pd.DataFrame({'Chunk Number': range(1, chunk_counter + 1), 'Chunk Length': chunk_lengths})
|
| 39 |
+
|
| 40 |
+
# return summarized_text, chunk_df, "summarized.txt"
|
| 41 |
+
|
| 42 |
+
|
| 43 |
+
# def read_file(file):
|
| 44 |
+
# print(file[0].name)
|
| 45 |
+
# with open(file[0].name, 'r') as file_:
|
| 46 |
+
# content = file_.read()
|
| 47 |
+
# return content
|
| 48 |
+
|
| 49 |
+
|
| 50 |
+
# def summarize_text_file(file):
|
| 51 |
+
# if file is not None:
|
| 52 |
+
# content = read_file(file)
|
| 53 |
+
# return summarize_text(content)
|
| 54 |
+
|
| 55 |
+
|
| 56 |
+
# input_type = gr.inputs.File("text")
|
| 57 |
+
|
| 58 |
+
# # Name the outputs using the label parameter and provide a download option
|
| 59 |
+
# demo = gr.Interface(fn=summarize_text_file, inputs=input_type,
|
| 60 |
+
# outputs=[gr.Textbox(label="Summarized Text"),
|
| 61 |
+
# gr.Dataframe(label="Chunk Information", type="pandas"),
|
| 62 |
+
# gr.File(label="Download Summarized Text", type="file", live=False)],
|
| 63 |
+
# title = "Text Summarization",
|
| 64 |
+
# description = "Summarize text using BART",
|
| 65 |
+
# theme = "huggingface",
|
| 66 |
+
# allow_flagging="never",
|
| 67 |
+
# live=True)
|
| 68 |
+
|
| 69 |
+
# demo.launch(share=True)
|