SpeechRecognition Python 函式庫

Python 的口語語言處理

Daniel Bourke

Machine Learning Engineer/YouTube Creator

為什麼選用 SpeechRecognition？

常見的 Python 語音函式庫

CMU Sphinx
Kaldi
SpeechRecognition
Facebook 的 Wav2letter++

開始使用 SpeechRecognition

從 PyPi 安裝：

$ pip install SpeechRecognition

相容 Python 2 與 3
我們將使用 Python 3

使用 Recognizer 類別

# Import the SpeechRecognition library
import speech_recognition as sr

# Create an instance of Recognizer
recognizer = sr.Recognizer()

# Set the energy threshold
recognizer.energy_threshold = 300

用 Recognizer 進行語音識別

Recognizer 類別提供可與語音 API 互動的內建函式
- recognize_bing()
- recognize_google()
- recognize_google_cloud()
- recognize_wit()

輸入：audio_file

輸出：從 audio_file 轉寫的語音

SpeechRecognition 範例

本段聚焦 recognize_google()
用 SpeechRecognition 從音訊檔進行語音識別：

# Import SpeechRecognition library
import speech_recognition as sr

# Instantiate Recognizer class
recognizer = sr.Recognizer()

# Transcribe speech using Google web API
recognizer.recognize_google(audio_data=audio_file,
                            language="en-US")

Learning speech recognition on DataCamp is awesome!

換你了！

Python 的口語語言處理