python-docs-samples/speech/api/speech_rest.py at numpy · deekshapai12/python-docs-samples · GitHub

History

87 lines (75 loc) · 2.86 KB

Raw

#!/usr/bin/env python

# Licensed under the Apache License, Version 2.0 (the "License");

# you may not use this file except in compliance with the License.

# You may obtain a copy of the License at

# http://www.apache.org/licenses/LICENSE-2.0

# Unless required by applicable law or agreed to in writing, software

# distributed under the License is distributed on an "AS IS" BASIS,

# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.

# See the License for the specific language governing permissions and

# limitations under the License.

"""Google Cloud Speech API sample application using the REST API for batch

processing."""

# [START import_libraries]

import argparse

import base64

import json

from googleapiclient import discovery

import httplib2

from oauth2client.client import GoogleCredentials

# [END import_libraries]

# [START authenticating]

DISCOVERY_URL = ('https://{api}.googleapis.com/$discovery/rest?'

'version={apiVersion}')

# Application default credentials provided by env variable

# GOOGLE_APPLICATION_CREDENTIALS

def get_speech_service():

credentials = GoogleCredentials.get_application_default().create_scoped(

['https://www.googleapis.com/auth/cloud-platform'])

http = httplib2.Http()

credentials.authorize(http)

return discovery.build(

'speech', 'v1beta1', http=http, discoveryServiceUrl=DISCOVERY_URL)

# [END authenticating]

def main(speech_file):

"""Transcribe the given audio file.

Args:

speech_file: the name of the audio file.

"""

# [START construct_request]

with open(speech_file, 'rb') as speech:

# Base64 encode the binary audio file for inclusion in the JSON

# request.

speech_content = base64.b64encode(speech.read())

service = get_speech_service()

service_request = service.speech().syncrecognize(

body={

'config': {

# There are a bunch of config options you can specify. See

# https://goo.gl/EPjAup for the full list.

'encoding': 'LINEAR16', # raw 16-bit signed LE samples

'sampleRate': 16000, # 16 khz

# See https://goo.gl/DPeVFW for a list of supported languages.

'languageCode': 'en-US', # a BCP-47 language tag

'audio': {

'content': speech_content.decode('UTF-8')

}

})

# [END construct_request]

# [START send_request]

response = service_request.execute()

print(json.dumps(response))

# [END send_request]

# [START run_application]

if __name__ == '__main__':

parser = argparse.ArgumentParser()

parser.add_argument(

'speech_file', help='Full path of audio file to be recognized')

args = parser.parse_args()

main(args.speech_file)

# [END run_application]

python-docs-samples/speech/api/speech_rest.py at numpy · deekshapai12/python-docs-samples · GitHub

Expand file tree

Breadcrumbs

speech_rest.py

Latest commit

History

Breadcrumbs

speech_rest.py

File metadata and controls