Problems with Google Cloud Speech-to-Text API

Question

I'm trying to transcribe a German podcast which I have both on my pc and my Google Storage bucket. I'm using this tutorial as a reference.

Here's my code:

frame_rate, channels = frame_rate_channel('pod.wav')
gcs_uri = 'gs://callsaudiofiles21/pod.wav'

client = speech.SpeechClient()
audio = types.RecognitionAudio(uri=gcs_uri)

config = types.RecognitionConfig(
encoding=enums.RecognitionConfig.AudioEncoding.LINEAR16,
sample_rate_hertz=frame_rate,
language_code='de-DE')

transcript = ''

operation = client.long_running_recognize(config, audio)
response = operation.result(timeout=10000)

for result in response.results:
    transcript += result.alternatives[0].transcript

But it stops at the operation line, outputting TypeError: long_running_recognize() takes from 1 to 2 positional arguments but 3 were given . The tutorial is from a year ago, so something must have changed in the API since. I'm not sure what to modify though.

Answer 1

Looks like you're using an old library version.

From Google async recognizion example , this two options seems to be equivalent:

    operation = client.long_running_recognize(
        request={"config": config, "audio": audio}
    )

or

    operation = client.long_running_recognize(config=config, audio=audio)

BTW - Take a look also at the official Google Codelab for Speech to text - they always have up-to-date examples.

Answer 2

Have you tried this:

operation = client.long_running_recognize(
        request={"config": config, "audio": audio}
    )