Ufdjrw

I have a code which takes videos from an input folder, converts it into audio file(.wav) using ffmpeg.
It then converts the audio file to text by recording 30 seconds audio (dura=30) and converting it to text using google translate api.

The problem is that the code takes a lot of time to convert video to text and it drops first two words and some words after every 30 seconds.

import speech_recognition as sr
import sys
import shutil
from googletrans import Translator
from pathlib import Path
import os
import wave
def audio_to_text(self,video_lst,deploy_path,video_path,audio_path):
 try:
 txt_lst=[]
 for video_file in video_lst:
 file_part=video_file.split('.')
 audio_path_mod = audio_path +'/'+ '.'.join(file_part[:-1])
 dir_path=video_path+'.'.join(file_part[:-1])
 self.createDirectory(audio_path_mod)
 audio_file='.'.join(file_part[:-1])+'.wav'
 command_ffmpeg='set PATH=%PATH%;'+deploy_path.replace('config','script')+'audio_video/ffmpeg/bin/'
 command='ffmpeg -i '+video_path+'/'+video_file+' '+audio_path_mod+'/'+audio_file
 os.system(command_ffmpeg)
 os.system(command)
 r=sr.Recognizer()
 dura=30
 lang='en'
 wav_filename=audio_path_mod+'/'+audio_file

 f = wave.open(wav_filename, 'r')
 frames = f.getnframes()
 rate = f.getframerate()
 audio_duration = frames / float(rate)
 final_text_lst=[]
 counter=0

 with sr.AudioFile(wav_filename) as source:
 while counter<audio_duration:
 audio=r.record(source,duration=dura)
 counter+=dura
 try:
 str=r.recognize_google(audio)
 final_text_lst.append(str)
 except Exception as e:
 print(e)
 print('Text data generated..')

 text_path=audio_path_mod+'/'+audio_file.replace('.wav','_audio_text.csv')
 with open(text_path, 'w') as f:
 f.write(' '.join(final_text_lst))

 except Exception as e:
 print(e)

Any help/suggestion would be valuable. Thanks in advance.