Create utils.py

utils.py

@@ -0,0 +1,92 @@
+import numpy as np
+import pandas as pd
+from sklearn.metrics import label_ranking_average_precision_score
+import streamlit as st 
+import joblib
+import os
+from translate import Translator
+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 
+import stanfordnlp
+def welcome():
+    return "Welcome All"
+
+def get_large_audio_transcription(path):  
+    r = sr.Recognizer()
+    sound = AudioSegment.from_wav(path)  
+    chunks = split_on_silence(sound,
+        min_silence_len = 500,
+        silence_thresh = sound.dBFS-14,
+        keep_silence=500,
+    )
+    whole_text = ""
+    for i, audio_chunk in enumerate(chunks, start=1):
+        chunk_filename = os.path.join(f"chunk{i}.wav")
+        audio_chunk.export(chunk_filename, format="wav")
+        with sr.AudioFile(chunk_filename) as source:
+            audio_listened = r.record(source)
+            try:
+                text = r.recognize_google(audio_listened)
+            except sr.UnknownValueError as e:
+                print("Error:", str(e))
+            else:
+                text = f"{text.capitalize()}. "
+                whole_text += text
+    return whole_text
+
+def get_translation(source, dest, text):
+
+    #src = "en"
+    #dst = "hi"
+
+    lang_dict = {
+        'Hindi': 'hi',
+    #    'English':'en',
+        'Malayalam': 'ml',
+        'Marathi': 'mr',
+        'Kannada':'kn', 
+        'Telugu':'te', 
+        'Tamil':'ta', 
+        'Oriya':'or',
+        'Bengali':'bn',
+        'Gujarati':'gu', 
+        'Urdu':'ur'
+    }
+
+    #src = lang_dict[source]
+    dst = lang_dict[dest]
+
+    #task_name = f"translation_{src}_to_{dst}"
+    #model_name = f"Helsinki-NLP/opus-mt-{src}-{dst}"
+
+    #translator  = pipeline(task_name, model=model_name, tokenizer=model_name)
+    translator = Translator(from_lang = 'en', to_lang=dst)
+    a_list = nltk.tokenize.sent_tokenize(text)
+    trans = []
+    for i in a_list: 
+        translation = translator.translate(i)
+        trans.append(translation)
+    
+    return ' '.join(trans)
+    
+
+def truecasing_by_sentence_segmentation(input_text):
+    # split the text into sentences
+    sentences = sent_tokenize(input_text, language='english')
+    # capitalize the sentences
+    sentences_capitalized = [s.capitalize() for s in sentences]
+    # join the capitalized sentences
+    text_truecase = re.sub(" (?=[\.,'!?:;])", "", ' '.join(sentences_capitalized))
+    return text_truecase