File size: 4,755 Bytes
135d3c0
7fbfa44
 
04cba07
884e1bf
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7fbfa44
 
 
 
884e1bf
 
 
 
 
036fae7
884e1bf
 
 
 
5ca455e
 
135d3c0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5ca455e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
"""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)