I'm trying to use the example code from the google page to transcribe a 30min .wav file. I changed the original code a bit and it's below:
from google.cloud import speech
from google.cloud.speech import enums
from google.cloud.speech import types
os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = 'C:\\Users\\louie\\Desktop\\PSC.json'
gcs_uri = os.path.join('C:\\Users\\louie\\Desktop','Untitled1.wav')
client = speech.SpeechClient()
audio = types.RecognitionAudio(uri=gcs_uri)
config = types.RecognitionConfig(
encoding=enums.RecognitionConfig.AudioEncoding.LINEAR16,
sample_rate_hertz=44100,
language_code='en-US')
operation = client.long_running_recognize(config, audio)
print('Waiting for operation to complete...')
response = operation.result(timeout=90)
# Each result is for a consecutive portion of the audio. Iterate through
# them to get the transcripts for the entire audio file.
for result in response.results:
# The first alternative is the most likely one for this portion.
print(u'Transcript: {}'.format(result.alternatives[0].transcript))
print('Confidence: {}'.format(result.alternatives[0].confidence))
When I run it, I got the error 400 Request contains an invalid argument I'm pretty sure my pre-setings are correct since the code for short transcription works for me. Could someone help me out on this issue? Thanks!
Edit: I think this issue is related to the wrong format of gcs_uri. Is there a way of transcribing large audio files without upload it to the Google cloud storage?
I noticed that gcs_uri should actually refer to the directory in the Google cloud. The format should be like gs://<bucket_name>/<file_path_inside_bucket>