Classifying transcribed speech with Sklearn

Spoken Language Processing in Python

Daniel Bourke

Machine Learning Engineer/YouTube creator

Inspecting the data

# Inspect post purchase audio folder
import os
post_purchase_audio = os.listdir("post_purchase")
print(post_purchase_audio[:5])

['post-purchase-audio-0.mp3',
  'post-purchase-audio-1.mp3',
  'post-purchase-audio-2.mp3',
  'post-purchase-audio-3.mp3',
  'post-purchase-audio-4.mp3']

Converting to wav

# Loop through mp3 files
for file in post_purchase_audio:
  print(f"Converting {file} to .wav...")
  # Use previously made function to convert to .wav
  convert_to_wav(file)

Converting post-purchase-audio-0.mp3 to .wav...
Converting post-purchase-audio-1.mp3 to .wav...
Converting post-purchase-audio-2.mp3 to .wav...
Converting post-purchase-audio-3.mp3 to .wav...
Converting post-purchase-audio-4.mp3 to .wav...

Transcribing all phone call excerpts

# Transcribe text from wav files
def create_text_list(folder):

  text_list = []

  # Loop through folder
  for file in folder:

    # Check for .wav extension
    if file.endswith(".wav"):

      # Transcribe audio
      text = transcribe_audio(file)

      # Add transcribed text to list
      text_list.append(text)

  return text_list

Transcribing all phone call excerpts

# Convert post purchase audio to text
post_purchase_text = create_text_list(post_purchase_audio)

print(post_purchase_text[:5])

['hey man I just water product from you guys and I think is amazing but I leave a little help setting it up',
 'these clothes I just bought from you guys too small is there anyway I can change the size',
 "I recently got these pair of shoes but they're too big can I change the size",
 "I bought a pair of pants from you guys but they're way too small",
 "I bought a pair of pants and they're the wrong colour is there any chance I can change that"]

Organizing transcribed text

import pandas as pd

# Create post purchase dataframe
post_purchase_df = pd.DataFrame({"label": "post_purchase", "text": post_purchase_text})

# Create pre purchase dataframe
pre_purchase_df = pd.DataFrame({"label": "pre_purchase", "text": pre_purchase_text})

# Combine pre purchase and post purhcase
df = pd.concat([post_purchase_df, pre_purchase_df])

# View the combined dataframe
df.head()

Organizing transcribed text

   label                                               text
0  post_purchase  yeah hello someone this morning delivered a pa...
1  post_purchase  my shipment arrived yesterday but it's not the...
2  post_purchase  hey my name is Daniel I received my shipment y...
3  post_purchase  hey mate how are you doing I'm just calling in...
4   pre_purchase  hey I was wondering if you know where my new p...

Building a text classifier

# Import text classification packages
import numpy as np
from sklearn.pipeline import Pipeline
from sklearn.naive_bayes import MultinomialNB
from sklearn.feature_extraction.text import CountVectorizer, TfidfTransformer
from sklearn.model_selection import train_test_split

# Split data into train and test sets
X_train, X_test, y_train, y_test = train_test_split(
    X=df["text"],
    y=df["label"],
    test_size=0.3)

Naive Bayes Pipeline

# Create text classifier pipeline
text_classifier = Pipeline([
  ("vectorizer", CountVectorizer()),
  ("tfidf", TfidfTransformer()),
  ("classifier", MultinomialNB())
])

# Fit the classifier pipeline on the training data
text_classifier.fit(X_train, y_train)

Not so Naive

# Make predictions and compare them to test labels
predictions = text_classifier.predict(X_test)

accuracy = 100 * np.mean(predictions == y_test.label)
print(f"The model is {accuracy:.2f}% accurate.")

The model is 97.87% accurate.

Let's practice!

Spoken Language Processing in Python