CODEWITHSUNDEEP
pythonspeechpyobjc
Алексндр Босов
Алексндр Босов

Reputation: 87

can not recognize speech from audio file with Speech framework

I've been using PyObjC for recognizing text from audio file applying Speech framework. So I check documentation and create this small script, but he was returning an error. What's my error?

import Speech


def record():
    recognize_request = Speech.SFSpeechRecognizer()
    if not recognize_request.isAvailable():
        raise NotImplementedError
    nsurl = Speech.NSURL.fileURLWithPath_(u"/Users/aleksandr/PycharmProjects/flask/file.wav")

    request = Speech.SFSpeechURLRecognitionRequest.alloc().initWithURL_(nsurl)
    function = lambda func, err: func.bestTranscription.formattedString()
    out = recognize_request.recognitionTaskWithRequest_resultHandler_(request, function)
    return function(out, None)


print(record())

Error:

AttributeError: '_SFSpeechRecognitionBlockTask' object has no attribute 'bestTranscription'

I expect a a string with recognized text.

Upvotes: 0

Views: 8

Answers (0)

Related Questions