Audiobestanden lezen met SpeechRecognition

Spoken Language Processing in Python

Daniel Bourke

Machine Learning Engineer/YouTube Creator

De AudioFile-klasse

import speech_recognition as sr

# Herkenner-instantie opzetten
recognizer = sr.Recognizer()

# Audiobestand inlezen
clean_support_call = sr.AudioFile("clean-support-call.wav")

# Type van clean_support_call controleren
type(clean_support_call)

<class 'speech_recognition.AudioFile'>

Van AudioFile naar AudioData

recognizer.recognize_google(audio_data=clean_support_call)

AssertionError: ``audio_data`` must be audio data

# Converteren van AudioFile naar AudioData
with clean_support_call as source:

    # Audio opnemen
    clean_support_call_audio = recognizer.record(source)

# Type controleren
type(clean_support_call_audio)

<class 'speech_recognition.AudioData'>

Onze AudioData transcriberen

# Schone supportcall transcriberen
recognizer.recognize_google(audio_data=clean_support_call_audio)

hallo ik wil graag hulp bij het instellen van mijn account alstublieft

Duration en offset

duration en offset zijn standaard beide None

# Laat duration en offset op standaard staan
with clean_support_call as source:
    clean_support_call_audio = recognizer.record(source,
                                                 duration=None,
                                                 offset=None)

# Eerste 2 seconden van de call
with clean_support_call as source:
    clean_support_call_audio = recognizer.record(source,
                                                 duration=2.0)

hallo ik wil graag

Laten we oefenen!

Spoken Language Processing in Python