Mentranskripsikan audio

import base64

from google.cloud import speech_v1p1beta1
import google.auth
from google.auth.transport import requests
from google.api_core.client_options import ClientOptions

audience="https://ENDPOINT:443"
api_endpoint="ENDPOINT:443"

def get_client(creds):
  opts = ClientOptions(api_endpoint=api_endpoint)
  return speech_v1p1beta1.SpeechClient(credentials=creds, client_options=opts)

def main():
  creds = None
  try:
    creds, project_id = google.auth.default()
    creds = creds.with_gdch_audience(audience)
    req = requests.Request()
    creds.refresh(req)
    print("Got token: ")
    print(creds.token)
  except Exception as e:
    print("Caught exception" + str(e))
    raise e
  return creds

def speech_func(creds):
  tc = get_client(creds)

  content="BASE64_ENCODED_AUDIO"

  audio = speech_v1p1beta1.RecognitionAudio()
  audio.content = base64.standard_b64decode(content)
  config = speech_v1p1beta1.RecognitionConfig()
  config.encoding= speech_v1p1beta1.RecognitionConfig.AudioEncoding.ENCODING
  config.sample_rate_hertz=RATE_HERTZ
  config.language_code="LANGUAGE_CODE"
  config.audio_channel_count=CHANNEL_COUNT

  metadata = [("x-goog-user-project", "projects/PROJECT_ID")]
  resp = tc.recognize(config=config, audio=audio, metadata=metadata)
  print(resp)

if __name__=="__main__":
  creds = main()
  speech_func(creds)

python SCRIPT_NAME

import base64

# Import the client library.
from google.cloud import speech_v1p1beta1
from google.cloud.speech_v1p1beta1.services.speech import client
from google.api_core.client_options import ClientOptions

api_endpoint="ENDPOINT:443"

def get_client(creds):
  opts = ClientOptions(api_endpoint=api_endpoint)
  return client.SpeechClient(credentials=creds, client_options=opts)

# Specify the audio to transcribe.
tc = get_client(creds)
content = "BASE64_ENCODED_AUDIO"

audio = speech_v1p1beta1.RecognitionAudio()
audio.content = base64.standard_b64decode(content)

config = speech_v1p1beta1.RecognitionConfig(
    encoding=speech_v1p1beta1.RecognitionConfig.AudioEncoding.ENCODING,
    sample_rate_hertz=RATE_HERTZ,
    audio_channel_count=CHANNEL_COUNT,
    language_code="LANGUAGE_CODE",
    model="chirp"
)

# Detect speech in the audio file.
metadata = (("x-goog-user-project", "projects/PROJECT_ID"),)
response = tc.recognize(config=config, audio=audio, metadata=metadata)

for result in response.results:
    print("Transcript: {}".format(result.alternatives[0].transcript))

python SCRIPT_NAME