create app.py

app.py

@@ -0,0 +1,104 @@
+"""
+Created on Mon Mar 28 01:04:50 2022
+@author: adeep
+"""
+from fnmatch import translate
+import cv2 as cv
+import tempfile
+import numpy as np
+import pandas as pd
+import streamlit as st 
+import joblib
+import os
+from moviepy.editor import VideoFileClip
+import speech_recognition as sr
+from pydub import AudioSegment
+from pydub.silence import split_on_silence
+import transformers
+from transformers import pipeline
+import nltk
+nltk.download('punkt')
+nltk.download('averaged_perceptron_tagger')
+import nltk
+nltk.download('punkt')
+nltk.download('averaged_perceptron_tagger')
+from nltk.tokenize import sent_tokenize
+import re
+from utils import get_translation, welcome, get_large_audio_transcription
+
+from PIL import Image
+
+#import stanfordnlp
+
+def main():
+ 
+    
+    st.title("Summarize Text")
+    video = st.file_uploader("Choose a file", type=['mp4'])
+    button = st.button("Summarize")
+    
+    max_c = st.sidebar.slider('Select max words', 50, 500, step=10, value=150)
+    min_c = st.sidebar.slider('Select min words', 10, 450, step=10, value=50)
+    gen_summ = False
+    
+ 
+
+    with st.spinner("Running.."):
+    
+        if button and video:
+            tfile = tempfile.NamedTemporaryFile(delete=False)
+            tfile.write(video.read())
+            #st.write(tfile.name)
+            v = VideoFileClip(tfile.name)
+            v.audio.write_audiofile("movie.wav")
+            #st.video(video, format="video/mp4", start_time=0)
+            #st.audio("movie.wav")
+            whole_text=get_large_audio_transcription("movie.wav")
+            #st.write(whole_text)
+            #summarizer = pipeline("summarization")
+            #summarizer = pipeline("summarization", model="t5-base", tokenizer="t5-base", framework="pt")
+            summarizer = pipeline("summarization", model="t5-large", tokenizer="t5-large", framework="pt")
+            summarized = summarizer(whole_text, min_length=min_c, max_length=max_c)
+            summ=summarized[0]['summary_text']
+            #st.write(summ) 
+            gen_summ = True
+            #stf_nlp = stanfordnlp.Pipeline(processors='tokenize,mwt,pos')
+            #doc = stf_nlp(summ)
+            #l=[w.text.capitalize() if w.upos in ["PROPN","NNS"] else w.text for sent in doc.sentences for w in sent.words]
+            #text=" ".join(l)
+            #summ=truecasing_by_sentence_segmentation(summ)  
+            sentences = sent_tokenize(summ, language='english')
+            # capitalize the sentences
+            sentences_capitalized = [s.capitalize() for s in sentences]
+            # join the capitalized sentences
+            summ = re.sub(" (?=[\.,'!?:;])", "", ' '.join(sentences_capitalized))
+            
+            if 'summary' not in st.session_state:
+                st.session_state.summary=True
+                st.session_state.summarization = summ
+                
+
+
+    translate = st.sidebar.radio('Do you want to translate the text to any different language?', ('No', 'Yes'))
+
+    if translate == 'Yes' and gen_summ == True:
+        lang_list  = ['Hindi', 'Marathi', 'Malayalam', 'Kannada', 'Telugu', 'Tamil', 'Oriya', 'Bengali', 'Gujarati', 'Urdu']
+    
+        s_type = st.sidebar.selectbox('Select the Language in which you want to Translate:',lang_list) 
+        st.sidebar.write('You selected:', s_type)
+
+        if 'summary' in st.session_state:
+            summarized_text = st.session_state.summarization
+            st.write(summarized_text)
+        translation = get_translation(source='English', dest=s_type, text=summarized_text)
+
+        st.sidebar.write(translation)
+    elif translate == 'Yes' and gen_summ == False:
+        st.error("The summary has not been generated yet. Please generate the summary first and then translate")
+      
+    else:
+         st.write('')
+             
+if __name__ == '__main__':
+    
+    main()