note generator complete

NoteGenerate/.idea/.gitignore

+# Default ignored files
+/shelf/
+/workspace.xml

NoteGenerate/.idea/.name

+EduZone
\ No newline at end of file

NoteGenerate/.idea/EduZone.iml

+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="jdk" jdkName="Python 3.8 (new_env)" jdkType="Python SDK" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>
\ No newline at end of file

NoteGenerate/.idea/inspectionProfiles/Project_Default.xml

+<component name="InspectionProjectProfileManager">
+  <profile version="1.0">
+    <option name="myName" value="Project Default" />
+    <inspection_tool class="PyPackageRequirementsInspection" enabled="true" level="WARNING" enabled_by_default="true">
+      <option name="ignoredPackages">
+        <value>
+          <list size="32">
+            <item index="0" class="java.lang.String" itemvalue="opencv-python" />
+            <item index="1" class="java.lang.String" itemvalue="cmake" />
+            <item index="2" class="java.lang.String" itemvalue="numpy" />
+            <item index="3" class="java.lang.String" itemvalue="dlib" />
+            <item index="4" class="java.lang.String" itemvalue="thop" />
+            <item index="5" class="java.lang.String" itemvalue="scikit-image" />
+            <item index="6" class="java.lang.String" itemvalue="opencv-contrib-python" />
+            <item index="7" class="java.lang.String" itemvalue="wincertstore" />
+            <item index="8" class="java.lang.String" itemvalue="networkx" />
+            <item index="9" class="java.lang.String" itemvalue="tifffile" />
+            <item index="10" class="java.lang.String" itemvalue="Flask-Cors" />
+            <item index="11" class="java.lang.String" itemvalue="PyYAML" />
+            <item index="12" class="java.lang.String" itemvalue="torch" />
+            <item index="13" class="java.lang.String" itemvalue="torchvision" />
+            <item index="14" class="java.lang.String" itemvalue="mysql-connector-python" />
+            <item index="15" class="java.lang.String" itemvalue="pandas" />
+            <item index="16" class="java.lang.String" itemvalue="tqdm" />
+            <item index="17" class="java.lang.String" itemvalue="regex" />
+            <item index="18" class="java.lang.String" itemvalue="mediapipe" />
+            <item index="19" class="java.lang.String" itemvalue="seaborn" />
+            <item index="20" class="java.lang.String" itemvalue="better-profanity" />
+            <item index="21" class="java.lang.String" itemvalue="colorama" />
+            <item index="22" class="java.lang.String" itemvalue="PyWavelets" />
+            <item index="23" class="java.lang.String" itemvalue="imutils" />
+            <item index="24" class="java.lang.String" itemvalue="pytz" />
+            <item index="25" class="java.lang.String" itemvalue="torchaudio" />
+            <item index="26" class="java.lang.String" itemvalue="Flask" />
+            <item index="27" class="java.lang.String" itemvalue="Pillow" />
+            <item index="28" class="java.lang.String" itemvalue="flashtext" />
+            <item index="29" class="java.lang.String" itemvalue="unidecode" />
+            <item index="30" class="java.lang.String" itemvalue="sklearn" />
+            <item index="31" class="java.lang.String" itemvalue="nltk" />
+          </list>
+        </value>
+      </option>
+    </inspection_tool>
+  </profile>
+</component>
\ No newline at end of file

NoteGenerate/.idea/inspectionProfiles/profiles_settings.xml

+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>
\ No newline at end of file

NoteGenerate/.idea/misc.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.8 (new_env)" project-jdk-type="Python SDK" />
+  <component name="PyCharmProfessionalAdvertiser">
+    <option name="shown" value="true" />
+  </component>
+</project>
\ No newline at end of file

NoteGenerate/.idea/modules.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/EduZone.iml" filepath="$PROJECT_DIR$/.idea/EduZone.iml" />
+    </modules>
+  </component>
+</project>
\ No newline at end of file

NoteGenerate/api.py

+from flask import Flask, request, render_template, send_file
+from flask_cors import CORS
+import werkzeug
+import cv2
+import note_generator.note as note_gen
+import topics_find.audio_gen as topic_gen
+import note_generator.write_word as writer
+import topics_find.bert as bert
+
+app = Flask(__name__)
+CORS(app)
+
+video_file_name = ''
+pptx_file_name = ''
+
+
+@app.route('/')
+def index():
+    return render_template('index.html')
+
+
+@app.route('/upload_action', methods=['GET', 'POST'])
+def upload_action():
+    lecture_video = request.files['lecture_video']
+    filename_v = werkzeug.utils.secure_filename(lecture_video.filename)
+    print("\nReceived image File name : " + lecture_video.filename)
+    lecture_video.save('upload/' + filename_v)
+
+    lecture_ppt = request.files['lecture_ppt']
+    filename = werkzeug.utils.secure_filename(lecture_ppt.filename)
+    print("\nReceived image File name : " + lecture_ppt.filename)
+    lecture_ppt.save('upload/' + filename)
+
+    global video_file_name
+    global pptx_file_name
+
+    video_file_name = filename_v
+    pptx_file_name = filename
+
+    return render_template('upload.html', video_file_name=video_file_name, pptx_file_name=pptx_file_name)
+
+
+@app.route('/generate_short_note', methods=['GET', 'POST'])
+def generate_short_note():
+    global video_file_name
+    global pptx_file_name
+
+    text_from_pptx = note_gen.generate_note('upload/' + pptx_file_name)
+    text_list_from_video, all_text = topic_gen.split_video_file('upload/' + video_file_name)
+
+    writer.create_doc()
+
+    writer.write_note('short note from lecture video :- ')
+    for i in text_list_from_video:
+        writer.write_note(i[1])
+
+    writer.write_note('short note from lecture slide (pptx) :- ')
+    writer.write_note(text_from_pptx)
+
+    writer.save_note('upload/' + pptx_file_name.split('.')[0] + '.docx')
+
+    doc_filename = pptx_file_name.split('.')[0] + '.docx'
+    print(doc_filename)
+
+    return render_template('short_notes.html', filename=doc_filename)
+
+
+@app.route('/generate_topics', methods=['GET', 'POST'])
+def generate_topics():
+    global video_file_name
+    global pptx_file_name
+
+    text_list_from_video, all_text = topic_gen.split_video_file('upload/' + video_file_name)
+
+    topic_list = []
+    for index in text_list_from_video:
+        topic_list.append([index[0], index[1], bert.get_topics_new(index[1])])
+
+    return render_template('topics.html', topic_list=topic_list)
+
+
+@app.route('/short_note/<name>')
+def short_note(name):
+    doc = 'upload\\' + str(name) + '.docx'
+    print('request', doc)
+    return send_file(doc, as_attachment=True)
+
+
+if __name__ == '__main__':
+    app.run(host="0.0.0.0", port=5200, debug=True)

NoteGenerate/note_generator/grammer.py

+import language_check
+tool = language_check.LanguageTool('en-US')
+text = 'A sentence with a error in the Hitchhiker’s Guide tot he Galaxy'
+matches = tool.check(text)
+
+matches[0].fromy, matches[0].fromx
+matches[0].ruleId, matches[0].replacements
+matches[1].fromy, matches[1].fromx
+matches[1].ruleId, matches[1].replacements
+
+print(matches[1])
+language_check.correct(text, matches)
\ No newline at end of file

NoteGenerate/note_generator/note.py

+from pptx import Presentation
+import glob
+from pptx.enum.shapes import MSO_SHAPE_TYPE
+import note_generator.ocr as ocr
+import note_generator.write_word as writer
+
+
+def iter_picture_shapes(prs):
+    for slide in prs.slides:
+        for shape in slide.shapes:
+            if shape.shape_type == MSO_SHAPE_TYPE.PICTURE:
+                yield shape
+
+
+def generate_note(filename):
+    count = 1
+    prs = Presentation(filename)
+    # writer.create_doc()
+    total_string = ''
+    print(filename)
+    print("----------------------")
+    for slide in prs.slides:
+        for shape in slide.shapes:
+            if hasattr(shape, "text"):
+                print(shape.text)
+                # writer.write_note(shape.text)
+                total_string += str(shape.text) + ' '
+    for picture in iter_picture_shapes(Presentation(filename)):
+        image = picture.image
+        # ---get image "file" contents---
+        image_bytes = image.blob
+        # ---make up a name for the file, e.g. 'image.jpg'---
+        image_filename = 'note_generator/image_data/' + str(count) + '.%s' % image.ext
+        count += 1
+        with open(image_filename, 'wb') as f:
+            f.write(image_bytes)
+        # writer.write_image(image_filename)
+        # ocr part - this will slow down system
+        easy_ocr_text = ocr.get_ocr(image_filename)
+        if easy_ocr_text != 'Did not found any text by ocr' and easy_ocr_text != 'Unable to read by ocr':
+            total_string += str(easy_ocr_text) + ' '
+        print(easy_ocr_text)
+    count += 1
+
+    # writer.save_note(str(filename).split('.')[0])
+    return total_string

NoteGenerate/note_generator/ocr.py

+import easyocr
+
+
+def get_ocr(path):
+    try:
+        reader = easyocr.Reader(['en'])
+        print(path)
+        result = reader.readtext(path)
+        if result[0][1] is not None:
+            return result[0][1]
+        else:
+            return 'Did not found any text by ocr'
+    except:
+        return 'Unable to read by ocr'

NoteGenerate/note_generator/text_output/.txt

+{'alternative': [{'transcript': 'two baby chicks headphone very own eggs when they would ask returned home from gathering food for 24 x 7 Pro Kabaddi final anywhere natural on what you discover the Lion treks around her to for it tracks therefore be determined the final babies', 'confidence': 0.8750093}, {'transcript': 'two baby chicks headphone very own eggs when they would ask that returned home from gathering food for 24 x 7 Pro Kabaddi final anywhere natural on what you discover the Lion treks around her to for it tracks therefore be determined to find her babies'}, {'transcript': 'water to baby chicks headphone very own eggs when they would ask that returned home from gathering food for 24 x 7 Pro Kabaddi final anywhere natural on what you discover the Lion treks around her to for it tracks therefore be determined the final babies'}, {'transcript': 'two baby chicks headphone very own eggs when they would ask returned home from gathering food for 24 x 7 Pro Kabaddi final anywhere natural on what you discover the Lion treks around her to for it tracks therefore be determined to find her babies'}, {'transcript': 'water to baby chicks headphone very own eggs when they would ask returned home from gathering food for 24 x 7 Pro Kabaddi final anywhere natural on what you discover the Lion treks around her to for it tracks therefore be determined the final babies'}], 'final': True}
\ No newline at end of file

NoteGenerate/note_generator/write_word.py

+import docx
+
+mydoc = None
+
+
+def create_doc():
+    global mydoc
+    mydoc = docx.Document()
+    mydoc.add_heading("Short Note", 0)
+
+
+def write_heading(text):
+    global mydoc
+    mydoc.add_heading(text, 2)
+
+
+def write_note(text):
+    global mydoc
+    mydoc.add_paragraph(text)
+
+
+def write_image(filename):
+    global mydoc
+    mydoc.add_picture(filename, width=docx.shared.Inches(5), height=docx.shared.Inches(7))
+
+
+def save_note(filename):
+    global mydoc
+    mydoc.save(filename + '.docx')

NoteGenerate/static/css/main.css

+
+.html { 
+	height: 100%; 
+}
+* {box-sizing: border-box;}
+
+.body { 
+	margin: 0;  
+	height: 100%; 
+	font-family: Arial, Helvetica, sans-serif;	
+	background-image:  url( ../images/bg.jpg )
+}
+
+.body_login {
+	height:50%;
+	width: 50%;
+	padding: 10px;
+	margin: 60px auto;
+	font-family: Arial, Helvetica, sans-serif;
+	background-image:  url( ../images/bg.jpg )
+}
+
+.header {
+	overflow: hidden;
+	background-color: #e28743;
+	padding: 5px 10px;
+}
+
+.header a {
+	float: left;
+	color: White;
+	text-align: center;
+	padding: 12px;
+	text-decoration: none;
+	font-size: 18px; 
+	line-height: 25px;
+	border-radius: 4px;
+}
+
+.header a.logo {
+	font-size: 25px;
+	font-weight: bold;
+}
+
+.header a:hover {
+	background-color: #76b5c5;
+	color: black;
+}
+
+.header a.active {
+	background-color: #76b5c5;
+	color: white;
+}
+
+.header-right {
+	float: right;
+}
+
+@media screen and (max-width: 500px) {
+  .header a {
+	float: none;
+	display: block;
+	text-align: left;
+  }
+  
+  .header-right {
+	float: none;
+  }
+}
+.global-container{
+	height:100%;
+	display: flex;
+	align-items: center;
+	justify-content: center;
+	float: left;
+	width: 100%;
+}
+
+.login-form {
+	opacity: 0.9;
+	width: 340px;
+	margin: 50px auto;
+	font-size: 15px;
+} 
+
+.login-form form {
+	margin-bottom: 15px;
+	background: #f7f7f7;
+	box-shadow: 0px 2px 2px rgba(0, 0, 0, 0.3);
+	padding: 30px;
+}
+
+.login-form h2 {
+	margin: 0 0 15px;
+}
+
+.form-control, .btn {
+	min-height: 38px;
+	border-radius: 2px;
+}
+
+.btn {        
+	font-size: 15px;
+	font-weight: bold;
+}
+
+form{
+	padding-top: 10px;
+	font-size: 14px;
+	margin-top: 30px;
+}
+
+.card-title{ font-weight:300; }
+
+.card{opacity: 0.9;}
+
+.effect7{
+	position:relative;
+	-webkit-box-shadow:0 1px 20px rgba(0, 0, 0, 0.3), 0 0 40px rgba(0, 0, 0, 0.1) inset;
+	-moz-box-shadow:0 1px 20px rgba(0, 0, 0, 0.3), 0 0 40px rgba(0, 0, 0, 0.1) inset;
+	box-shadow:0 1px 20px rgba(0, 0, 0, 0.3), 0 0 40px rgba(0, 0, 0, 0.1) inset;
+}
+
+.btn{
+	font-size: 14px;
+	margin-top:20px;
+}
+
+.login-form{ 
+	width:700px;
+	margin:20px;
+}
+
+.sign-up{
+	text-align:center;
+	padding:20px 0 0;
+}
+
+.alert{
+	margin-bottom:-30px;
+	font-size: 13px;
+	margin-top:20px;
+}
+
+.modal-dialog {
+	max-width: 800px;
+	margin: 30px auto;
+}
+
+.modal-body {
+	position:relative;
+	padding:0px;
+}
+
+.close {
+	position:absolute;
+	right:-30px;
+	top:0;
+	z-index:999;
+	font-size:2rem;
+	font-weight: normal;
+	color:#fff;
+	opacity:1;
+}
+
+.custom-file-uploader {
+	position: relative;
+	input[type='file'] {
+		display: block;
+		position: absolute;
+		top: 0;
+		right: 0;
+		bottom: 0;
+		left: 0;
+		z-index: 5;
+		width: 100%;
+		height: 100%;
+		opacity: 0;
+		cursor: default;
+	}
+}
\ No newline at end of file

NoteGenerate/static/css/style.css

+/* Always set the map height explicitly to define the size of the div
+       * element that contains the map. */
+#map {
+  height: 100%;
+}
+
+/* Optional: Makes the sample page fill the window. */
+html,
+body {
+  height: 100%;
+  margin: 0;
+  padding: 0;
+}
\ No newline at end of file

NoteGenerate/static/js/index.js

+const citymap = {
+  chicago: {
+    center: { lat: 6.9061, lng: 79.9696 },
+    population: 100,
+  }
+};
+
+function initMap() {
+  // Create the map.
+  const map = new google.maps.Map(document.getElementById("map"), {
+    zoom: 15,
+    center: { lat: 6.9061, lng: 79.9696 },
+    mapTypeId: "terrain",
+  });
+
+  // Construct the circle for each value in citymap.
+  // Note: We scale the area of the circle based on the population.
+  for (const city in citymap) {
+    // Add the circle for this city to the map.
+    const cityCircle = new google.maps.Circle({
+      strokeColor: "#FF0000",
+      strokeOpacity: 0.8,
+      strokeWeight: 2,
+      fillColor: "#FF0000",
+      fillOpacity: 0.35,
+      map,
+      center: citymap[city].center,
+      radius: Math.sqrt(citymap[city].population) * 100,
+    });
+  }
+}
\ No newline at end of file

NoteGenerate/static/js/main.js

+document.querySelectorAll(".drop-zone__input").forEach((inputElement) => {
+  const dropZoneElement = inputElement.closest(".drop-zone");
+
+  dropZoneElement.addEventListener("click", (e) => {
+    inputElement.click();
+  });
+
+  inputElement.addEventListener("change", (e) => {
+    if (inputElement.files.length) {
+      updateThumbnail(dropZoneElement, inputElement.files[0]);
+    }
+  });
+
+  dropZoneElement.addEventListener("dragover", (e) => {
+    e.preventDefault();
+    dropZoneElement.classList.add("drop-zone--over");
+  });
+
+  ["dragleave", "dragend"].forEach((type) => {
+    dropZoneElement.addEventListener(type, (e) => {
+      dropZoneElement.classList.remove("drop-zone--over");
+    });
+  });
+
+  dropZoneElement.addEventListener("drop", (e) => {
+    e.preventDefault();
+
+    if (e.dataTransfer.files.length) {
+      inputElement.files = e.dataTransfer.files;
+      updateThumbnail(dropZoneElement, e.dataTransfer.files[0]);
+    }
+
+    dropZoneElement.classList.remove("drop-zone--over");
+  });
+});
+
+/**
+ * Updates the thumbnail on a drop zone element.
+ *
+ * @param {HTMLElement} dropZoneElement
+ * @param {File} file
+ */
+function updateThumbnail(dropZoneElement, file) {
+  let thumbnailElement = dropZoneElement.querySelector(".drop-zone__thumb");
+
+  // First time - remove the prompt
+  if (dropZoneElement.querySelector(".drop-zone__prompt")) {
+    dropZoneElement.querySelector(".drop-zone__prompt").remove();
+  }
+
+  // First time - there is no thumbnail element, so lets create it
+  if (!thumbnailElement) {
+    thumbnailElement = document.createElement("div");
+    thumbnailElement.classList.add("drop-zone__thumb");
+    dropZoneElement.appendChild(thumbnailElement);
+  }
+
+  thumbnailElement.dataset.label = file.name;
+
+  // Show thumbnail for image files
+  if (file.type.startsWith("image/")) {
+    const reader = new FileReader();
+
+    reader.readAsDataURL(file);
+    reader.onload = () => {
+      thumbnailElement.style.backgroundImage = `url('${reader.result}')`;
+    };
+  } else {
+    thumbnailElement.style.backgroundImage = null;
+  }
+}
\ No newline at end of file

NoteGenerate/templates/index.html

+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <title>Index</title>
+    <meta charset="utf-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1">
+    <link rel="stylesheet" href="https://maxcdn.bootstrapcdn.com/bootstrap/3.4.1/css/bootstrap.min.css">
+    <script src="https://ajax.googleapis.com/ajax/libs/jquery/3.5.1/jquery.min.js"></script>
+    <script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.4.1/js/bootstrap.min.js"></script>
+</head>
+<style>
+	html {
+		height: 100%;
+	}
+	* {box-sizing: border-box;}
+
+	body {
+		margin: 0;
+		height: 100%;
+		font-family: Arial, Helvetica, sans-serif;
+		background-image: url({{ url_for('static', filename='images/bg.jpg') }})
+	}
+
+
+	.header {
+		overflow: hidden;
+		background-color: #970103;
+		padding: 5px 10px;
+	}
+
+	.header a {
+		float: left;
+		color: White;
+		text-align: center;
+		padding: 12px;
+		text-decoration: none;
+		font-size: 18px;
+		line-height: 25px;
+		border-radius: 4px;
+	}
+
+	.header a.logo {
+		font-size: 25px;
+		font-weight: bold;
+	}
+
+	.header a:hover {
+		background-color: #8a8a8a;
+		color: black;
+	}
+
+	.header a.active {
+		background-color: #0b0b0b;
+		color: white;
+	}
+
+	.header-right {
+		float: right;
+	}
+
+	@media screen and (max-width: 500px) {
+	  .header a {
+		float: none;
+		display: block;
+		text-align: left;
+	  }
+
+	  .header-right {
+		float: none;
+	  }
+	}
+
+   .global-container{
+		margin-top: 20px;
+		display: flex;
+		align-items: center;
+		justify-content: center;
+		float: left;
+		width: 100%;
+	}
+
+	form{
+		padding-top: 10px;
+		font-size: 14px;
+		margin-top: 30px;
+		margin-left: 50px;
+		margin-right: 50px;
+	}
+
+	.card-title{ font-weight:300; }
+
+	.card{opacity: 0.95;}
+
+	.effect7{
+		position:relative;
+		-webkit-box-shadow:0 1px 20px rgba(0, 0, 0, 0.3), 0 0 40px rgba(0, 0, 0, 0.1) inset;
+		-moz-box-shadow:0 1px 20px rgba(0, 0, 0, 0.3), 0 0 40px rgba(0, 0, 0, 0.1) inset;
+        box-shadow:0 1px 20px rgba(0, 0, 0, 0.3), 0 0 40px rgba(0, 0, 0, 0.1) inset;
+	}
+	.login-form{
+		width:1175px;
+		margin:20px;
+	}
+
+
+.drop-zone {
+  max-width: 300px;
+  height: 300px;
+  padding: 25px;
+  display: flex;
+  align-items: center;
+  justify-content: center;
+  text-align: center;
+  font-family: "Quicksand", sans-serif;
+  font-weight: 500;
+  font-size: 20px;
+  cursor: pointer;
+  color: #cccccc;
+  border: 4px dashed #345BDE;
+  border-radius: 10px;
+}
+
+.drop-zone--over {
+  border-style: solid;
+}
+
+.drop-zone__input {
+  display: none;
+}
+
+.drop-zone__thumb {
+  width: 100%;
+  height: 100%;
+  border-radius: 10px;
+  overflow: hidden;
+  background-color: #cccccc;
+  background-size: cover;
+  position: relative;
+}
+
+.drop-zone__thumb::after {
+  content: attr(data-label);
+  position: absolute;
+  bottom: 0;
+  left: 0;
+  width: 100%;
+  padding: 5px 0;
+  color: #ffffff;
+  background: rgba(0, 0, 0, 0.75);
+  font-size: 14px;
+  text-align: center;
+}
+
+
+
+
+
+
+
+
+
+
+</style>
+<body>
+
+
+<div class="global-container">
+    <br>
+    <br>
+    <br>
+    <div class="card login-form effect7">
+        <div class="card-body">
+            <center>
+                <h3>Please Upload Lecture and Slides</h3>
+            </center>
+            <form action="upload_action" method="post" enctype="multipart/form-data">
+                <div class="form-group">
+                    <h5>Please Select Lecture</h5>
+                    <input type="file" name="lecture_video" class="form" accept="video/mp4,video/x-m4v,video/*"
+                           required>
+                </div>
+                <div class="form-group">
+                    <h5>Please Select Slides</h5>
+                    <input type="file" name="lecture_ppt" class="form" accept=".ppt, .pptx" required>
+                </div>
+                <div class="form-group">
+                    <button type="submit" class="btn btn-primary btn-block">upload</button>
+                </div>
+            </form>
+
+        </div>
+    </div>
+</div>
+</body>
+</html>

NoteGenerate/templates/short_notes.html

+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <title>Short Note</title>
+    <meta charset="utf-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1">
+    <link rel="stylesheet" href="https://maxcdn.bootstrapcdn.com/bootstrap/3.4.1/css/bootstrap.min.css">
+    <script src="https://ajax.googleapis.com/ajax/libs/jquery/3.5.1/jquery.min.js"></script>
+    <script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.4.1/js/bootstrap.min.js"></script>
+</head>
+<style>
+	html {
+		height: 100%;
+	}
+	* {box-sizing: border-box;}
+
+	body {
+		margin: 0;
+		height: 100%;
+		font-family: Arial, Helvetica, sans-serif;
+		background-image: url({{ url_for('static', filename='images/bg.jpg') }})
+	}
+
+
+	.header {
+		overflow: hidden;
+		background-color: #970103;
+		padding: 5px 10px;
+	}
+
+	.header a {
+		float: left;
+		color: White;
+		text-align: center;
+		padding: 12px;
+		text-decoration: none;
+		font-size: 18px;
+		line-height: 25px;
+		border-radius: 4px;
+	}
+
+	.header a.logo {
+		font-size: 25px;
+		font-weight: bold;
+	}
+
+	.header a:hover {
+		background-color: #8a8a8a;
+		color: black;
+	}
+
+	.header a.active {
+		background-color: #0b0b0b;
+		color: white;
+	}
+
+	.header-right {
+		float: right;
+	}
+
+	@media screen and (max-width: 500px) {
+	  .header a {
+		float: none;
+		display: block;
+		text-align: left;
+	  }
+
+	  .header-right {
+		float: none;
+	  }
+	}
+
+   .global-container{
+		margin-top: 20px;
+		display: flex;
+		align-items: center;
+		justify-content: center;
+		float: left;
+		width: 100%;
+	}
+
+	form{
+		padding-top: 10px;
+		font-size: 14px;
+		margin-top: 50px;
+		margin-left: 50px;
+		margin-right: 50px;
+	}
+
+	.card-title{ font-weight:300; }
+
+	.card{
+	opacity: 0.95;
+
+	}
+
+	.card-body{
+  margin-top: 100px;
+
+	}
+
+	.effect7{
+		position:relative;
+		-webkit-box-shadow:0 1px 20px rgba(0, 0, 0, 0.3), 0 0 40px rgba(0, 0, 0, 0.1) inset;
+		-moz-box-shadow:0 1px 20px rgba(0, 0, 0, 0.3), 0 0 40px rgba(0, 0, 0, 0.1) inset;
+        box-shadow:0 1px 20px rgba(0, 0, 0, 0.3), 0 0 40px rgba(0, 0, 0, 0.1) inset;
+	}
+	.login-form{
+		width:1175px;
+		margin:20px;
+	}
+
+
+
+
+
+
+
+
+
+
+
+</style>
+<body>
+
+
+<div class="global-container">
+    <br>
+    <br>
+    <br>
+    <div class="card login-form effect7">
+        <div class="card-body">
+            <center>
+                <h2>Short Note Ready</h2>
+                <a href="/short_note/{{filename}}" style="color:red;">Download as doc file</a>
+            </center>
+
+
+
+        </div>
+    </div>
+</div>
+</body>
+</html>

NoteGenerate/templates/topics.html

+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <title>Topics</title>
+    <meta charset="utf-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1">
+    <link rel="stylesheet" href="https://maxcdn.bootstrapcdn.com/bootstrap/3.4.1/css/bootstrap.min.css">
+    <script src="https://ajax.googleapis.com/ajax/libs/jquery/3.5.1/jquery.min.js"></script>
+    <script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.4.1/js/bootstrap.min.js"></script>
+</head>
+<style>
+	html {
+		height: 100%;
+	}
+	* {box-sizing: border-box;}
+
+	body {
+		margin: 0;
+		height: 100%;
+		font-family: Arial, Helvetica, sans-serif;
+		background-image: url({{ url_for('static', filename='images/bg.jpg') }})
+	}
+
+
+	.header {
+		overflow: hidden;
+		background-color: #970103;
+		padding: 5px 10px;
+	}
+
+	.header a {
+		float: left;
+		color: White;
+		text-align: center;
+		padding: 12px;
+		text-decoration: none;
+		font-size: 18px;
+		line-height: 25px;
+		border-radius: 4px;
+	}
+
+	.header a.logo {
+		font-size: 25px;
+		font-weight: bold;
+	}
+
+	.header a:hover {
+		background-color: #8a8a8a;
+		color: black;
+	}
+
+	.header a.active {
+		background-color: #0b0b0b;
+		color: white;
+	}
+
+	.header-right {
+		float: right;
+	}
+
+	@media screen and (max-width: 500px) {
+	  .header a {
+		float: none;
+		display: block;
+		text-align: left;
+	  }
+
+	  .header-right {
+		float: none;
+	  }
+	}
+
+   .global-container{
+		margin-top: 20px;
+		display: flex;
+		align-items: center;
+		justify-content: center;
+		float: left;
+		width: 100%;
+	}
+
+	form{
+		padding-top: 10px;
+		font-size: 14px;
+		margin-top: 50px;
+		margin-left: 50px;
+		margin-right: 50px;
+	}
+
+	.card-title{ font-weight:300; }
+
+	.card{
+	opacity: 0.95;
+
+	}
+
+	.card-body{
+  margin-top: 100px;
+
+	}
+
+	.effect7{
+		position:relative;
+		-webkit-box-shadow:0 1px 20px rgba(0, 0, 0, 0.3), 0 0 40px rgba(0, 0, 0, 0.1) inset;
+		-moz-box-shadow:0 1px 20px rgba(0, 0, 0, 0.3), 0 0 40px rgba(0, 0, 0, 0.1) inset;
+        box-shadow:0 1px 20px rgba(0, 0, 0, 0.3), 0 0 40px rgba(0, 0, 0, 0.1) inset;
+	}
+	.login-form{
+		width:1175px;
+		margin:20px;
+	}
+
+
+
+
+
+
+
+
+
+
+
+
+</style>
+<body>
+
+
+<div class="global-container">
+    <br>
+    <br>
+    <br>
+    <div class="card login-form effect7">
+        <div class="card-body">
+            <center>
+                <h2>Topics Ready</h2>
+            </center>
+            <table class="table" id="table">
+                <thead>
+                <tr>
+                    <th>Index</th>
+                    <th>Key Points ( Topics )</th>
+                </tr>
+                </thead>
+                <tbody>
+                {% for row in topic_list %}
+                <tr>
+                    <td>{{row[0]}}</td>
+                    <td>{{row[2]}}</td>
+
+                </tr>
+                 {% endfor %}
+                </tbody>
+            </table>
+
+
+        </div>
+    </div>
+</div>
+</body>
+</html>

NoteGenerate/templates/upload.html

+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <title>Upload</title>
+    <meta charset="utf-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1">
+    <link rel="stylesheet" href="https://maxcdn.bootstrapcdn.com/bootstrap/3.4.1/css/bootstrap.min.css">
+    <script src="https://ajax.googleapis.com/ajax/libs/jquery/3.5.1/jquery.min.js"></script>
+    <script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.4.1/js/bootstrap.min.js"></script>
+</head>
+<style>
+	html {
+		height: 100%;
+	}
+	* {box-sizing: border-box;}
+
+	body {
+		margin: 0;
+		height: 100%;
+		font-family: Arial, Helvetica, sans-serif;
+		background-image: url({{ url_for('static', filename='images/bg.jpg') }})
+	}
+
+
+	.header {
+		overflow: hidden;
+		background-color: #970103;
+		padding: 5px 10px;
+	}
+
+	.header a {
+		float: left;
+		color: White;
+		text-align: center;
+		padding: 12px;
+		text-decoration: none;
+		font-size: 18px;
+		line-height: 25px;
+		border-radius: 4px;
+	}
+
+	.header a.logo {
+		font-size: 25px;
+		font-weight: bold;
+	}
+
+	.header a:hover {
+		background-color: #8a8a8a;
+		color: black;
+	}
+
+	.header a.active {
+		background-color: #0b0b0b;
+		color: white;
+	}
+
+	.header-right {
+		float: right;
+	}
+
+	@media screen and (max-width: 500px) {
+	  .header a {
+		float: none;
+		display: block;
+		text-align: left;
+	  }
+
+	  .header-right {
+		float: none;
+	  }
+	}
+
+   .global-container{
+		margin-top: 20px;
+		display: flex;
+		align-items: center;
+		justify-content: center;
+		float: left;
+		width: 100%;
+	}
+
+	form{
+		padding-top: 10px;
+		font-size: 14px;
+		margin-top: 50px;
+		margin-left: 50px;
+		margin-right: 50px;
+	}
+
+	.card-title{ font-weight:300; }
+
+	.card{
+	opacity: 0.95;
+
+	}
+
+	.card-body{
+  margin-top: 100px;
+
+	}
+
+	.effect7{
+		position:relative;
+		-webkit-box-shadow:0 1px 20px rgba(0, 0, 0, 0.3), 0 0 40px rgba(0, 0, 0, 0.1) inset;
+		-moz-box-shadow:0 1px 20px rgba(0, 0, 0, 0.3), 0 0 40px rgba(0, 0, 0, 0.1) inset;
+        box-shadow:0 1px 20px rgba(0, 0, 0, 0.3), 0 0 40px rgba(0, 0, 0, 0.1) inset;
+	}
+	.login-form{
+		width:1175px;
+		margin:20px;
+	}
+
+
+
+
+
+
+
+
+
+
+
+</style>
+<body>
+
+
+<div class="global-container">
+    <br>
+    <br>
+    <br>
+    <div class="card login-form effect7">
+        <div class="card-body">
+            <center>
+                <h2>File uploaded successfully</h2>
+                <h4 style="color:red;">Note generation and topic analysing will take some time</h4>
+            </center>
+
+            <form>
+                <h4>Lecture Video File : {{video_file_name}}</h4>
+                <h4>Lecture Slide File (pptx) : {{pptx_file_name}}</h4>
+                <div class="form-group">
+                    <a href="/generate_short_note" class="btn btn-primary btn-block">Generate Short Note</a>
+                </div>
+                <div class="form-group">
+                    <a href="/generate_topics" class="btn btn-primary btn-block">Analyse Topics</a>
+                </div>
+            </form>
+
+        </div>
+    </div>
+</div>
+</body>
+</html>

NoteGenerate/topics_find/audio_gen.py

+import moviepy.editor as mp
+from moviepy.video.io.ffmpeg_tools import ffmpeg_extract_subclip
+from moviepy.editor import VideoFileClip
+import os
+from topics_find import text_gen
+
+
+def convert_video_to_audio(filename):
+    clip = mp.VideoFileClip(r"" + filename)
+    audio_file_name = str(filename).split('/')[-1].replace('.mp4', '.wav')
+
+    clip.audio.write_audiofile(r"topics_find/audio_input/" + audio_file_name)
+
+    return text_gen.convert_audio_to_text("topics_find/audio_input/" + audio_file_name)
+
+
+def split_video_file(filename):
+    return_list = []
+    all_text = ''
+
+    required_video_file = filename
+
+    files = os.listdir('topics_find/video_input')
+
+    for filename in files:
+        os.remove('topics_find/video_input/' + filename)
+
+    total_length = VideoFileClip(required_video_file).duration
+    print(total_length)
+
+    no_of_slices = int(total_length / 50) + 1
+
+    time_grid = []
+
+    for i in range(0, no_of_slices):
+        time_grid.append(i * 50)
+
+    for i in range(no_of_slices):
+        if i == len(time_grid) - 1:
+            # ffmpeg_extract_subclip(required_video_file, time_grid[i], total_length - time_grid[i],
+            #                        targetname='videos/' + str(i) + ".mp4")
+            pass
+        else:
+            ffmpeg_extract_subclip(required_video_file, time_grid[i], time_grid[i + 1],
+                                   targetname='topics_find/video_input' + str(i) + ".mp4")
+            text = convert_video_to_audio('topics_find/video_input' + str(i) + ".mp4")
+            all_text += text + ' '
+            return_list.append([i, text])
+
+    return return_list, all_text

NoteGenerate/topics_find/bert.py

+import nltk
+import topics_find.question_generator as q_gen
+
+# nltk.download('words')
+
+# from bertopic import BERTopic
+from nltk.corpus import words
+
+# model = BERTopic(verbose=True)
+
+
+def get_topics(file):
+    topics_outputs = []
+
+    docs = []
+    with open(file) as file:
+        for line in file:
+            docs.append(line.rstrip())
+
+    topics, probabilities = model.fit_transform(docs)
+    #
+    print(model.get_topic_freq())
+    #
+    print('done')
+    #
+    # model.get_topic_freq().head(11)
+
+    print(model.get_topics())
+
+    for i in model.get_topic(0):
+        if i[0] in words.words():
+            pass
+        else:
+            print(i[0])
+            topics_outputs.append(i[0])
+
+    return topics_outputs
+
+
+def get_topics_new(text):
+    topics = q_gen.get_keywords(text, q_gen.summarizer(text))
+    print(topics)
+    return topics

NoteGenerate/topics_find/question_generator.py

+from textwrap3 import wrap
+import torch
+from transformers import T5ForConditionalGeneration, T5Tokenizer
+import random
+import numpy as np
+import nltk
+# nltk.download('punkt')
+# nltk.download('brown')
+# nltk.download('wordnet')
+# nltk.download('stopwords')
+from nltk.corpus import wordnet as wn
+from nltk.tokenize import sent_tokenize
+from nltk.corpus import stopwords
+import string
+import pke
+import traceback
+from flashtext import KeywordProcessor
+
+summary_model = T5ForConditionalGeneration.from_pretrained('t5-base')
+summary_tokenizer = T5Tokenizer.from_pretrained('t5-base')
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+summary_model = summary_model.to(device)
+
+
+def set_seed(seed: int):
+    random.seed(seed)
+    np.random.seed(seed)
+    torch.manual_seed(seed)
+    torch.cuda.manual_seed_all(seed)
+
+
+def postprocesstext(content):
+    final = ""
+    for sent in sent_tokenize(content):
+        sent = sent.capitalize()
+        final = final + " " + sent
+    return final
+
+
+def summarizer(text, model=summary_model, tokenizer=summary_tokenizer):
+    text = text.strip().replace("\n", " ")
+    text = "summarize: " + text
+    # print (text)
+    max_len = 512
+    encoding = tokenizer.encode_plus(text, max_length=max_len, pad_to_max_length=False, truncation=True,
+                                     return_tensors="pt").to(device)
+
+    input_ids, attention_mask = encoding["input_ids"], encoding["attention_mask"]
+
+    outs = model.generate(input_ids=input_ids,
+                          attention_mask=attention_mask,
+                          early_stopping=True,
+                          num_beams=3,
+                          num_return_sequences=1,
+                          no_repeat_ngram_size=2,
+                          min_length=75,
+                          max_length=300)
+
+    dec = [tokenizer.decode(ids, skip_special_tokens=True) for ids in outs]
+    summary = dec[0]
+    summary = postprocesstext(summary)
+    summary = summary.strip()
+
+    return summary
+
+
+def get_nouns_multipartite(content):
+    out = []
+    try:
+        extractor = pke.unsupervised.MultipartiteRank()
+        extractor.load_document(input=content)
+        #    not contain punctuation marks or stopwords as candidates.
+        pos = {'PROPN', 'NOUN'}
+        # pos = {'PROPN','NOUN'}
+        stoplist = list(string.punctuation)
+        stoplist += ['-lrb-', '-rrb-', '-lcb-', '-rcb-', '-lsb-', '-rsb-']
+        stoplist += stopwords.words('english')
+        extractor.candidate_selection(pos=pos, stoplist=stoplist)
+        # 4. build the Multipartite graph and rank candidates using random walk,
+        #    alpha controls the weight adjustment mechanism, see TopicRank for
+        #    threshold/method parameters.
+        extractor.candidate_weighting(alpha=1.1,
+                                      threshold=0.75,
+                                      method='average')
+        keyphrases = extractor.get_n_best(n=15)
+
+        for val in keyphrases:
+            out.append(val[0])
+    except:
+        out = []
+        traceback.print_exc()
+
+    return out
+
+
+def get_keywords(originaltext, summarytext):
+    keywords = get_nouns_multipartite(originaltext)
+    print("keywords unsummarized: ", keywords)
+    keyword_processor = KeywordProcessor()
+    for keyword in keywords:
+        keyword_processor.add_keyword(keyword)
+
+    keywords_found = keyword_processor.extract_keywords(summarytext)
+    keywords_found = list(set(keywords_found))
+    print("keywords_found in summarized: ", keywords_found)
+
+    important_keywords = []
+    for keyword in keywords:
+        if keyword in keywords_found:
+            important_keywords.append(keyword)
+
+    return important_keywords[:4]
+
+
+question_model = T5ForConditionalGeneration.from_pretrained('ramsrigouthamg/t5_squad_v1')
+question_tokenizer = T5Tokenizer.from_pretrained('ramsrigouthamg/t5_squad_v1')
+question_model = question_model.to(device)
+
+
+def get_question(context, answer, model, tokenizer):
+    text = "context: {} answer: {}".format(context, answer)
+    encoding = tokenizer.encode_plus(text, max_length=384, pad_to_max_length=False, truncation=True,
+                                     return_tensors="pt").to(device)
+    input_ids, attention_mask = encoding["input_ids"], encoding["attention_mask"]
+
+    outs = model.generate(input_ids=input_ids,
+                          attention_mask=attention_mask,
+                          early_stopping=True,
+                          num_beams=5,
+                          num_return_sequences=1,
+                          no_repeat_ngram_size=2,
+                          max_length=72)
+
+    dec = [tokenizer.decode(ids, skip_special_tokens=True) for ids in outs]
+
+    Question = dec[0].replace("question:", "")
+    Question = Question.strip()
+    return Question
+
+
+def generate_questions_and_answers(text):
+    set_seed(42)
+    summarized_text = summarizer(text, summary_model, summary_tokenizer)
+    imp_keywords = get_keywords(text, summarized_text)
+    question_and_answer_list = []
+    for answer in imp_keywords:
+        ques = get_question(summarized_text, answer, question_model, question_tokenizer)
+        question_and_answer_list.append([ques, answer.capitalize()])
+
+    return question_and_answer_list
+
+# xxx = """Elon Musk has shown again he can influence the digital currency market with just his tweets. After saying that his electric vehicle-making company
+# Tesla will not accept payments in Bitcoin because of environmental concerns, he tweeted that he was working with developers of Dogecoin to improve
+# system transaction efficiency. Following the two distinct statements from him, the world's largest cryptocurrency hit a two-month low, while Dogecoin
+# rallied by about 20 percent. The SpaceX CEO has in recent months often tweeted in support of Dogecoin, but rarely for Bitcoin.  In a recent tweet,
+# Musk put out a statement from Tesla that it was “concerned” about the rapidly increasing use of fossil fuels for Bitcoin (price in India) mining and
+# transaction, and hence was suspending vehicle purchases using the cryptocurrency.  A day later he again tweeted saying, “To be clear, I strongly
+# believe in crypto, but it can't drive a massive increase in fossil fuel use, especially coal”.  It triggered a downward spiral for Bitcoin value but
+# the cryptocurrency has stabilised since.   A number of Twitter users welcomed Musk's statement. One of them said it's time people started realising
+# that Dogecoin “is here to stay” and another referred to Musk's previous assertion that crypto could become the world's future currency."""
+
+
+# print(generate_questions_and_answers(xxx))
+#
+# x = generate_questions_and_answers(xxx)
+#
+# for i in x:
+#     print(i[0])
+#     print(i[1])

NoteGenerate/topics_find/summary.py

+import glob
+from pptx import Presentation
+import math
+import nltk
+from nltk.corpus import stopwords
+from nltk.tokenize import word_tokenize, sent_tokenize
+import textract
+import os.path
+
+
+def create_sumall(abc, ratio):
+    if abc:
+        filename = abc
+        stop_word = ['is', 'a', 'and', 'the']
+
+        # Function to create Text summarization
+        def create_summ(text):
+            stopWords = set(stopwords.words("english"))
+            words = word_tokenize(text)
+            freqTable = dict()
+            for word in words:
+                word = word.lower()
+                if word in stopWords:
+                    continue
+                if word in freqTable:
+                    freqTable[word] += 1
+                else:
+                    freqTable[word] = 1
+
+            sentences = sent_tokenize(text)
+            sentenceValue = dict()
+
+            for sentence in sentences:
+                for word, freq in freqTable.items():
+                    if word in sentence.lower():
+                        if sentence in sentenceValue:
+                            sentenceValue[sentence] += freq
+                        else:
+                            sentenceValue[sentence] = freq
+
+            sumValues = 0
+            for sentence in sentenceValue:
+                sumValues += sentenceValue[sentence]
+
+            lensenvalu = len(sentenceValue)
+            if lensenvalu == 0:
+                lensenvalu = 1
+                average = int(sumValues / lensenvalu)
+            else:
+                average = int(sumValues / lensenvalu)
+
+            summary = ''
+            for sentence in sentences:
+                if (sentence in sentenceValue) and (sentenceValue[sentence] > (
+                        ratio * average)):
+                    summary += " " + sentence
+
+            return summary
+
+        def read_full_pptxe(filename):
+            sentences = []
+            b = []
+            a = 0
+            for eachfile in glob.glob(filename):
+                prs = Presentation(eachfile)
+                for slide in prs.slides:
+                    a = a + 1
+                    for shape in slide.shapes:
+                        if hasattr(shape, "text"):
+                            s = create_summ(shape.text.replace("\n", " "))
+                            s = str(s)
+                            if (len(s)) >= 1:
+                                f = ["Slide " + str(a) + "-" + s]
+                                sentences.append(f)
+            return sentences
+
+        def read_full_docx(filename):
+            sentences = []
+            text = textract.process(filename)
+            temp = text.split(".")
+            for t in temp:
+                sentences.append(t.replace("\n", " "))
+            return sentences
+
+        extension = os.path.splitext(filename)[1]
+
+        if extension == 'docx':
+            read_full_docx(filename)
+        else:
+            read_full_pptxe(filename)
+
+        def Convert(string):
+            li = list(string.split(" "))
+            return li
+
+        def Convert2(string):
+            li = list(string.split("\n"))
+            return li
+
+        def read_slide3(filename):
+            a = 1
+            for eachfile in glob.glob(filename):
+                prs = Presentation(eachfile)
+                for slide in prs.slides:
+                    a = a + 1
+                    for shape in slide.shapes:
+                        if hasattr(shape, "text"):
+                            if a == 4 and shape.shape_id == 3:
+                                s3 = str(shape.text)
+                                return s3
+
+        def read_full_pptx(filename, sss):
+            numberslide = []
+            numberslide.append(sss)
+            a = 0
+            for eachfile in glob.glob(filename):
+                prs = Presentation(eachfile)
+                for slide in prs.slides:
+                    a = a + 1
+                    for shape in slide.shapes:
+                        if hasattr(shape, "text"):
+                            if shape.shape_id != 2:
+                                s = shape.text.replace("\n", " ")
+                                s = str(s)
+                                if (len(s)) >= 20 and a != 3 and a != 1 and a != 2:
+                                    lo_1 = [a for a in new_l1 if a in s.lower()]
+                                    f_lo_l = round((len(lo_1) / len_of_l1) * 100)
+                                    if f_lo_l >= 50:
+                                        f = "Slide " + str(a)
+                                        numberslide.append(f)
+
+            return numberslide
+
+        loooo = Convert2(read_slide3(filename))
+
+        abc = []
+        for i in loooo:
+            l1 = Convert(i.lower())
+            new_l1 = [w for w in l1 if w not in stop_word]
+            len_of_l1 = len(new_l1)
+            read_full_pptx(filename, i)
+            abc.append(read_full_pptx(filename, i))
+
+        return (read_full_pptxe(filename), abc)
+    else:
+        print('error')

NoteGenerate/topics_find/test_api.py

+from flask import Flask, request, url_for, redirect, render_template
+from flask_cors import CORS
+import werkzeug
+import topics_find.summary as summarizeed
+import json
+import textract
+from pptx import Presentation
+import os
+
+app = Flask(__name__)
+CORS(app)
+
+
+@app.route('/summerize', methods=['GET', 'POST'])
+def summerize():
+    file = request.files['file']
+    ratio = float(request.form['ratio'])
+    filename = werkzeug.utils.secure_filename(file.filename)
+    print("\nReceived image File name : " + file.filename)
+    file.save('upload/' + filename)
+
+    f, file_extension = os.path.splitext('upload/' + filename)
+    print(file_extension)
+
+    if file_extension == '.docx':
+        text = textract.process('upload/' + filename)
+        arr = str(text).replace("\\n", "")
+        arr = arr.replace("\\t", "")
+        arr = arr.replace("\\", "")
+
+        prs = Presentation()
+
+        lyt = prs.slide_layouts[0]  # choosing a slide layout
+
+        for x in range(0, 3):
+
+            if x == 2:
+                slide = prs.slides.add_slide(lyt)  # adding a slide
+                title = slide.shapes.title  # assigning a title
+                subtitle = slide.placeholders[1]  # placeholder for subtitle
+                subtitle.text = arr
+            else:
+                slide = prs.slides.add_slide(lyt)  # adding a slide
+                title = slide.shapes.title  # assigning a title
+                subtitle = slide.placeholders[1]  # placeholder for subtitle
+                title.text = "ignore"  # title
+                subtitle.text = "ignore"  # subtitle
+        prs.save("upload/slide3.pptx")  # saving file
+        print('file saved')
+        res = summarizeed.create_sumall('upload/slide3.pptx', ratio)
+    else:
+        res = summarizeed.create_sumall('upload/' + filename, ratio)
+
+    rr = []
+    for r in res[0]:
+        rr.append(r[0].replace('"', ''))
+
+    return_str = '{ "result" : ['
+
+    for i in range(len(rr)):
+        if i == len(rr) - 1:
+            return_str += '"' + rr[i] + '"'
+        else:
+            return_str += '"' + rr[i] + '"' + ','
+    return_str += ']}'
+
+    print(return_str)
+
+    return json.loads(return_str)
+
+
+if __name__ == '__main__':
+    app.run(host="0.0.0.0", port=5005, debug=True)

NoteGenerate/topics_find/text_gen.py

+import speech_recognition as sr
+import subprocess
+import os
+import sys
+
+PYTHONIOENCODING = "UTF-8"
+
+FOLDER_AUDIO = "audio_input"
+FOLDER_TEXT = "text_output"
+LANGUAGE = "en-US"
+
+
+# print("starting...")
+#
+# if not os.path.isdir(FOLDER_AUDIO):
+#     os.mkdir(FOLDER_AUDIO)
+#
+# if not os.path.isdir(FOLDER_TEXT):
+#     os.mkdir(FOLDER_TEXT)
+#
+# paths = [os.path.join(FOLDER_AUDIO, nome) for nome in os.listdir(FOLDER_AUDIO)]
+# files = [arq for arq in paths if os.path.isfile(arq)]
+# wav_files = [arq for arq in files if arq.lower().endswith(".wav")]
+#
+# for filename in wav_files:
+#     r = sr.Recognizer()
+#     with sr.AudioFile(filename) as source:
+#         audio = r.record(source)
+#
+#     command = r.recognize_google(audio, language='en-IN', show_all=True)
+#     print(command)
+#
+#     print("running file {}".format(filename))
+#
+#     filefinal = filename.split("audio_input/")[1].split(".wav")[0]
+#     filefinal = '{}/{}.txt'.format(FOLDER_TEXT, filefinal)
+#     with open(filefinal, 'w') as arq:
+#         arq.write(str(command))
+#
+#     print("create a new file {}".format(filefinal))
+#
+# print("finish")
+
+
+def convert_audio_to_text(filename):
+    r = sr.Recognizer()
+    with sr.AudioFile(filename) as source:
+        audio = r.record(source)
+
+    try:
+        command = r.recognize_google(audio, language='en-IN', show_all=True)
+        print(command["alternative"][0]["transcript"])
+        return command["alternative"][0]["transcript"]
+
+    except:
+        return 'did not convert'
+
+# convert_audio_to_text('audio_input/3.wav')

NoteGenerate/topics_find/text_output/3.txt

+{'alternative': [{'transcript': 'type of diffusion is an IR module that making waves right now open source machine many more than the Legend images from text free ridiculously well with the engine is the ability to fusion took 256 180 hours and hours to train at market price that 612 and pigments', 'confidence': 0.88088202}, {'transcript': 'type of diffusion is an IR module that making waves right now open source machine many more than the Legend images from text free ridiculously well with the engine is the ability to fusion took 256 150 hours and hours to train at market price that 612 and pigments'}, {'transcript': 'type of diffusion is an IR module that making waves right now open source machine many more than the Legend images from text free ridiculously well with the engine is the ability to fusion took 256 180 days and hours to train at market price that 612 and pigments'}, {'transcript': 'type of diffusion is an IR module that making waves right now kitchen open source machine many more than the Legend images from text free ridiculously well with the engine is the ability to fusion took 256 150 hours and hours to train at market price that 612 and pigments'}, {'transcript': 'type of diffusion is an IR module that making waves right now open source machine many more than the Legend images from text free ridiculously well with the engine is the ability to fusion Tuk 256 150 hours and hours to train at market price that 612 and pigments'}], 'final': True}
\ No newline at end of file

NoteGenerate/topics_find/text_output/uil9h-hwq08.txt

+{'alternative': [{'transcript': 'two baby chicks headphone very own eggs when they would ask returned home from gathering food for 24 x 7 Pro Kabaddi final anywhere natural on what you discover the Lion treks around her to for it tracks therefore be determined the final babies', 'confidence': 0.87500781}, {'transcript': 'two baby chicks headphone very own eggs when they would ask that returned home from gathering food for 24 x 7 Pro Kabaddi final anywhere natural on what you discover the Lion treks around her to for it tracks therefore be determined to find her babies'}, {'transcript': 'water to baby chicks headphone very own eggs when they would ask that returned home from gathering food for 24 x 7 Pro Kabaddi final anywhere natural on what you discover the Lion treks around her to for it tracks therefore be determined the final babies'}, {'transcript': 'two baby chicks headphone very own eggs when they would ask returned home from gathering food for 24 x 7 Pro Kabaddi final anywhere natural on what you discover the Lion treks around her to for it tracks therefore be determined to find her babies'}, {'transcript': 'water to baby chicks headphone very own eggs when they would ask returned home from gathering food for 24 x 7 Pro Kabaddi final anywhere natural on what you discover the Lion treks around her to for it tracks therefore be determined the final babies'}], 'final': True}
\ No newline at end of file