ついにGAになった機械学習による音声認識サービス Cloud Speech APIを試してみよう!

#!/usr/bin/env python
# [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()
    # 処理する動画によってこの部分のパラメータを変える必要があります
    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': 'FLAC',  # 動画の形式
                'sampleRate': 16000,  #サンプリングレート               
　　　　 # See https://goo.gl/DPeVFW for a list of supported languages.
                'languageCode': 'ja-JA',  # どの言語で変換するか
            },
            'audio': {
                'content': speech_content.decode('UTF-8')
                }
            })
    # [END construct_request]
    # [START send_request]
    response = service_request.execute()
    for alt in response['results']:
      for t in alt['alternatives']:
       transcription =  t['transcript']
       print(transcription)
# [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]

#!/usr/bin/env python

# [START import_libraries]import argparse
import base64
import json
import time

from googleapiclient import discovery
import httplib2
from oauth2client.client import GoogleCredentials
# [END import_libraries]


# [START authenticating]


# 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)
# [END authenticating]
def main(speech_file):
    """Transcribe the given audio file asynchronously.
    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 request.
        speech_content = base64.b64encode(speech.read())
    service = get_speech_service()
   //呼び出すメソッドがsyncrecognizeからasyncrecognizeに
    service_request = service.speech().asyncrecognize(
        body={
            'config': {
                # There are a bunch of config options you can specify. See
                # https://goo.gl/EPjAup for the full list.
                'encoding': 'FLAC',  # raw 16-bit signed LE samples
                'sampleRate': 16000,  # 16 khz
                # See https://goo.gl/DPeVFW for a list of supported languages.
                'languageCode': 'ja-JA',  # a BCP-47 language tag
            },
            'audio': {
                'content': speech_content.decode('UTF-8')
                }
    })
    # [END construct_request]
    # [START send_request]
    response = service_request.execute()
    # [END send_request]
    name = response['name']
    print(name)
    # Construct a GetOperation request.
　//変換処理が完了するまでチェックし続ける
    service_request = service.operations().get(name=name)
    while True:
        # Give the server a few seconds to process.
        print('Waiting for server processing...')
        time.sleep(1)
        # Get the long running operation with response.
        response = service_request.execute()
        if 'done' in response and response['done']:
            break
    for alt in response['response']['results']:
      for t in alt['alternatives']:
       transcription =  t['transcript']
       print(transcription)
# [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]