File size: 3,348 Bytes
2e727c2
c81d8ab
2e727c2
 
 
 
 
 
 
 
 
 
fb658f7
c81d8ab
 
 
b588b2c
2e727c2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b451def
 
c81d8ab
 
 
b451def
c81d8ab
7cd8f48
 
 
 
c81d8ab
 
7cd8f48
b451def
 
 
b588b2c
 
b451def
 
 
b588b2c
2e727c2
 
 
 
 
 
 
 
 
b588b2c
 
2e727c2
 
 
 
 
 
 
c81d8ab
2e727c2
 
 
c81d8ab
 
2e727c2
 
b588b2c
2e727c2
 
 
b588b2c
fb658f7
b451def
c81d8ab
7cd8f48
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
import gradio as gr
from transformers import pipeline, AutoTokenizer
from sentence_transformers import SentenceTransformer, util

# Translation models
translation_models = {
    'Vietnamese': "Helsinki-NLP/opus-mt-en-vi",
    'Japanese': "Helsinki-NLP/opus-mt-en-jap",
    'Thai': "Helsinki-NLP/opus-mt-en-tha",
    'Spanish': "Helsinki-NLP/opus-mt-en-es"
}

# Initialize summarization pipeline with a specified model
model_name = "sshleifer/distilbart-cnn-12-6"
summarizer = pipeline("summarization", model=model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Initialize translation pipeline
def get_translator(language):
    model_name = translation_models.get(language)
    if model_name:
        return pipeline("translation", model=model_name)
    return None

# Helper function to generate bullet points
def generate_bullet_points(text):
    model = SentenceTransformer('paraphrase-MiniLM-L6-v2')
    sentences = text.split('. ')
    embeddings = model.encode(sentences, convert_to_tensor=True)
    clusters = util.community_detection(embeddings, threshold=0.75)
    
    bullet_points = []
    for cluster in clusters:
        cluster_sentences = [sentences[idx] for idx in cluster]
        main_sentence = cluster_sentences[0] if cluster_sentences else ""
        bullet_points.append(main_sentence.strip())
    
    return "\n".join(f"- {point}" for point in bullet_points)

# Helper function to split text into chunks
def split_text(text, max_tokens=1024):
    inputs = tokenizer(text, return_tensors='pt', truncation=False)
    input_ids = inputs['input_ids'][0]
    total_tokens = len(input_ids)
    
    chunks = []
    start = 0
    while start < total_tokens:
        end = min(start + max_tokens, total_tokens)
        chunk_ids = input_ids[start:end]
        chunk_text = tokenizer.decode(chunk_ids, skip_special_tokens=True)
        chunks.append(chunk_text)
        start = end
    
    return chunks

# Helper function to summarize text
def summarize_text(text):
    chunks = split_text(text)
    summaries = [summarizer(chunk, max_length=150, min_length=40, do_sample=False)[0]['summary_text'] for chunk in chunks]
    return " ".join(summaries)

# Helper function to translate text
def translate_text(text, language):
    translator = get_translator(language)
    if translator:
        translated_text = translator(text)[0]['translation_text']
        return translated_text
    return text

def process_text(input_text, language):
    summary = summarize_text(input_text)
    bullet_points = generate_bullet_points(summary)
    translated_text = translate_text(bullet_points, language)
    return bullet_points, translated_text

# Create Gradio interface
iface = gr.Interface(
    fn=process_text,
    inputs=[
        gr.Textbox(label="Input Text", placeholder="Paste your text here...", lines=10),
        gr.Dropdown(choices=["Vietnamese", "Japanese", "Thai", "Spanish"], label="Translate to", value="Vietnamese")
    ],
    outputs=[
        gr.Textbox(label="Bullet Points", lines=10),
        gr.Textbox(label="Translated Bullet Points", lines=10)
    ],
    title="Text to Bullet Points and Translation",
    description="Paste any text, and the program will summarize it into bullet points. Optionally, translate the bullet points into Vietnamese, Japanese, Thai, or Spanish."
)

iface.launch()