Creating transcription helper functions

Spoken Language Processing in Python

Daniel Bourke

Machine Learning Engineer/YouTube Creator

Exploring audio files

# Import os module
import os

# Check the folder of audio files
os.listdir("acme_audio_files")

(['call_1.mp3',
  'call_2.mp3',
  'call_3.mp3',
  'call_4.mp3'])

Preparing for the proof of concept

import speech_recognition as sr
from pydub import AudioSegment

# Import call 1 and convert to .wav
call_1 = AudioSegment.from_file("acme_audio_files/call_1.mp3")
call_1.export("acme_audio_files/call_1.wav", format="wav")

# Transcribe call 1
recognizer = sr.Recognizer()
call_1_file = sr.AudioFile("acme_audio_files/call_1.wav")
with call_1_file as source:
    call_1_audio = recognizer.record(call_1_file)
recognizer.recognize_google(call_1_audio)

Functions we'll create

convert_to_wav() converts non-.wav files to .wav files.
show_pydub_stats() shows the audio attributes of a .wav file.
transcribe_audio() uses recognize_google() to transcribe a .wav file.

Creating a file format conversion function

# Create function to convert audio file to wav
def convert_to_wav(filename):
  "Takes an audio file of non .wav format and converts to .wav"
  # Import audio file
  audio = AudioSegment.from_file(filename)

  # Create new filename
  new_filename = filename.split(".")[0] + ".wav"

  # Export file as .wav
  audio.export(new_filename, format="wav")
  print(f"Converting {filename} to {new_filename}...")

Using the file format conversion function

convert_to_wav("acme_studios_audio/call_1.mp3")

Converting acme_audio_files/call_1.mp3 to acme_audio_files/call_1.wav...

Creating an attribute showing function

def show_pydub_stats(filename):
  "Returns different audio attributes related to an audio file."
  # Create AudioSegment instance
  audio_segment = AudioSegment.from_file(filename)

  # Print attributes
  print(f"Channels: {audio_segment.channels}")
  print(f"Sample width: {audio_segment.sample_width}")
  print(f"Frame rate (sample rate): {audio_segment.frame_rate}")
  print(f"Frame width: {audio_segment.frame_width}")
  print(f"Length (ms): {len(audio_segment)}")
  print(f"Frame count: {audio_segment.frame_count()}")

Using the attribute showing function

show_pydub_stats("acme_audio_files/call_1.wav")

Channels: 2
Sample width: 2
Frame rate (sample rate): 32000
Frame width: 4
Length (ms): 54888
Frame count: 1756416.0

Creating a transcribe function

# Create a function to transcribe audio
def transcribe_audio(filename):
  "Takes a .wav format audio file and transcribes it to text."
  # Setup a recognizer instance
  recognizer = sr.Recognizer()


  # Import the audio file and convert to audio data
  audio_file = sr.AudioFile(filename)
  with audio_file as source:
    audio_data = recognizer.record(audio_file)

  # Return the transcribed text
  return recognizer.recognize_google(audio_data)

Using the transcribe function

transcribe_audio("acme_audio_files/call_1.wav")

"hello welcome to Acme studio support line my name is Daniel how can I best help 
you hey Daniel this is John I've recently bought a smart from you guys and I know 
that's not good to hear John let's let's get your cell number and then we 
can we can set up a way to fix it for you one number for 1757 varies how long do 
you reckon this is going to take about an hour now while John we're going to try 
our best hour I will we get the sealing member will start up this support case 
I'm just really really really really I've been trying to contact 34 been put on 
hold more than an hour and half so I'm not really happy I kind of wanna get this 
issue 6 is fossil"

Let's practice!

Spoken Language Processing in Python