Python으로 배우는 음성 언어 처리
Daniel Bourke
Machine Learning Engineer/YouTube creator
# 구매 후 오디오 폴더 확인
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']
# mp3 파일 반복 처리
for file in post_purchase_audio:
print(f"Converting {file} to .wav...")
# 기존 함수로 .wav 변환
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...
# wav 파일에서 텍스트 전사 def create_text_list(folder):text_list = []# 폴더 반복 for file in folder:# .wav 확장자 확인 if file.endswith(".wav"):# 오디오 전사 text = transcribe_audio(file)# 전사 텍스트 목록에 추가 text_list.append(text)return text_list
# 구매 후 오디오를 텍스트로 변환 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"]
import pandas as pd# 구매 후 데이터프레임 생성 post_purchase_df = pd.DataFrame({"label": "post_purchase", "text": post_purchase_text})# 구매 전 데이터프레임 생성 pre_purchase_df = pd.DataFrame({"label": "pre_purchase", "text": pre_purchase_text})
# 구매 전/후 결합
df = pd.concat([post_purchase_df, pre_purchase_df])
# 결합 데이터프레임 확인
df.head()
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...
# 텍스트 분류 패키지 임포트
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
# 학습/테스트 데이터 분할
X_train, X_test, y_train, y_test = train_test_split(
X=df["text"],
y=df["label"],
test_size=0.3)
# 텍스트 분류 파이프라인 생성
text_classifier = Pipeline([
("vectorizer", CountVectorizer()),
("tfidf", TfidfTransformer()),
("classifier", MultinomialNB())
])
# 학습 데이터로 파이프라인 학습
text_classifier.fit(X_train, y_train)
# 예측 후 테스트 라벨과 비교 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.
Python으로 배우는 음성 언어 처리