clearness of the speech

clearness.py

+import spacy
+from scipy.io.wavfile import read
+import numpy as np
+import matplotlib.pyplot as plt
+
+from pydub import AudioSegment
+import os
+import glob
+
+#Identify ocer complex words
+nlp = spacy.load("en_core_web_sm")
+doc = nlp("Apple is looking at buying U.K. startup for $1 billion accumulativeness. This ia a dog. <y name is Chalika Mihiran")
+for token in doc:
+    count = len(token)
+    if count > 12:
+        print(f"{token.text} - {count}: This is a too complicated word")
+
+#Identify over complex sentences
+for sent in doc.sents:
+    word_count = 0
+    # print(sent.text)
+    for words in sent:
+        # print(words.text)
+        word_count = word_count + 1
+    # print(word_count)
+
+
+sentence_tokens = [sent for sent in doc.sents]
+# print(sentence_tokens)
+
+# sentence_words = {}
+# word_count = 0
+# for sent in sentence_tokens:
+#     for token in sent:
+#         sentence_words[sent] = word_count + 1
+
+# print(sentence_words)
+
+#Calculate the rate of the speed
+# Read the Audiofile
+samplerate, data = read('C:/Users/CHALIKA PC/Desktop/Year 04/Research/Audio/videoplayback_1_.wav')
+# Frame rate for the Audio
+# print(samplerate)
+
+# Duration of the audio in Seconds
+duration = len(data)/samplerate
+print("Duration of Audio in Seconds", duration)
+print("Duration of Audio in Minutes", duration/60)
+
+# print(len(data))