Upload app.py
Browse files
app.py
ADDED
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# -*- coding: utf-8 -*-
|
2 |
+
"""
|
3 |
+
Created on Mon Mar 28 01:04:50 2022
|
4 |
+
|
5 |
+
@author: adeep
|
6 |
+
"""
|
7 |
+
from fnmatch import translate
|
8 |
+
import cv2 as cv
|
9 |
+
import tempfile
|
10 |
+
import numpy as np
|
11 |
+
import pandas as pd
|
12 |
+
import streamlit as st
|
13 |
+
import joblib
|
14 |
+
import os
|
15 |
+
from moviepy.editor import VideoFileClip
|
16 |
+
import speech_recognition as sr
|
17 |
+
from pydub import AudioSegment
|
18 |
+
from pydub.silence import split_on_silence
|
19 |
+
import transformers
|
20 |
+
from transformers import pipeline
|
21 |
+
import nltk
|
22 |
+
nltk.download('punkt')
|
23 |
+
nltk.download('averaged_perceptron_tagger')
|
24 |
+
import nltk
|
25 |
+
nltk.download('punkt')
|
26 |
+
nltk.download('averaged_perceptron_tagger')
|
27 |
+
from nltk.tokenize import sent_tokenize
|
28 |
+
import re
|
29 |
+
from utils import get_translation, welcome, get_large_audio_transcription
|
30 |
+
|
31 |
+
from PIL import Image
|
32 |
+
|
33 |
+
|
34 |
+
def main():
|
35 |
+
|
36 |
+
|
37 |
+
st.title("Summarize Text")
|
38 |
+
video = st.file_uploader("Choose a file", type=['mp4'])
|
39 |
+
button = st.button("Summarize")
|
40 |
+
|
41 |
+
max = st.sidebar.slider('Select max', 50, 500, step=10, value=150)
|
42 |
+
min = st.sidebar.slider('Select min', 10, 450, step=10, value=50)
|
43 |
+
|
44 |
+
with st.spinner("Generating Summary.."):
|
45 |
+
|
46 |
+
if button and video:
|
47 |
+
tfile = tempfile.NamedTemporaryFile(delete=False)
|
48 |
+
tfile.write(video.read())
|
49 |
+
#st.write(tfile.name)
|
50 |
+
v = VideoFileClip(tfile.name)
|
51 |
+
v.audio.write_audiofile("movie.wav")
|
52 |
+
#st.video(video, format="video/mp4", start_time=0)
|
53 |
+
st.audio("movie.wav")
|
54 |
+
whole_text=get_large_audio_transcription("movie.wav")
|
55 |
+
#st.write(whole_text)
|
56 |
+
#summarizer = pipeline("summarization")
|
57 |
+
summarizer = pipeline("summarization", model="t5-base", tokenizer="t5-base", framework="pt")
|
58 |
+
summarized = summarizer(whole_text, min_length=75, max_length=400)
|
59 |
+
summ=summarized[0]['summary_text']
|
60 |
+
st.write(summ)
|
61 |
+
|
62 |
+
if 'summary' not in st.session_state:
|
63 |
+
st.session_state.summary=True
|
64 |
+
st.session_state.summarization = summ
|
65 |
+
|
66 |
+
|
67 |
+
translate = st.sidebar.radio('Do you want to translate the text to any different language?', ('No', 'Yes'))
|
68 |
+
|
69 |
+
if translate == 'Yes':
|
70 |
+
lang_list = ['Hindi', 'Marathi', 'Malayalam', 'Kannada', 'Telugu', 'Tamil', 'Oriya', 'Bengali', 'Gujarati', 'Urdu']
|
71 |
+
|
72 |
+
s_type = st.sidebar.selectbox('Select the Language in which you want to Translate:',lang_list)
|
73 |
+
st.sidebar.write('You selected:', s_type)
|
74 |
+
|
75 |
+
if 'summary' in st.session_state:
|
76 |
+
summarized_text = st.session_state.summarization
|
77 |
+
st.write(summarized_text)
|
78 |
+
translation = get_translation(source='English', dest=s_type, text=summarized_text)
|
79 |
+
|
80 |
+
st.sidebar.write(translation)
|
81 |
+
|
82 |
+
|
83 |
+
if __name__ == '__main__':
|
84 |
+
|
85 |
+
main()
|