Membaca file audio dengan SpeechRecognition

Pemrosesan Bahasa Lisan dengan Python

Daniel Bourke

Machine Learning Engineer/YouTube Creator

Kelas AudioFile

import speech_recognition as sr

# Siapkan instance recognizer
recognizer = sr.Recognizer()

# Baca file audio
clean_support_call = sr.AudioFile("clean-support-call.wav")

# Periksa tipe clean_support_call
type(clean_support_call)

<class 'speech_recognition.AudioFile'>

Dari AudioFile ke AudioData

recognizer.recognize_google(audio_data=clean_support_call)

AssertionError: ``audio_data`` must be audio data

# Konversi dari AudioFile ke AudioData
with clean_support_call as source:

    # Rekam audio
    clean_support_call_audio = recognizer.record(source)

# Periksa tipenya
type(clean_support_call_audio)

<class 'speech_recognition.AudioData'>

Transkripsi AudioData kita

# Transkripsi panggilan dukungan bersih
recognizer.recognize_google(audio_data=clean_support_call_audio)

hello I'd like to get some help setting up my account please

Duration dan offset

duration dan offset keduanya None secara default

# Biarkan duration dan offset default
with clean_support_call as source:
    clean_support_call_audio = recognizer.record(source,
                                                 duration=None,
                                                 offset=None)

# Ambil 2 detik pertama panggilan dukungan
with clean_support_call as source:
    clean_support_call_audio = recognizer.record(source,
                                                 duration=2.0)

hello I'd like to get

Ayo berlatih!

Pemrosesan Bahasa Lisan dengan Python