Google speech service - not returning transcription

Question

I am using the sample code provided here and have implemented with the following:

# [START import_libraries]
import argparse
import base64
import json
import time
from oauth2client.service_account import ServiceAccountCredentials
import googleapiclient.discovery
import googleapiclient as gac
# [END import_libraries]


# [START authenticating]


# Application default credentials provided by env variable
# GOOGLE_APPLICATION_CREDENTIALS
def get_speech_service(credentials):
    return googleapiclient.discovery.build('speech', 'v1beta1',credentials = credentials)



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())

#    print speech_content

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

    credentials = ServiceAccountCredentials.from_json_keyfile_name(
        '/Users/user/Documents/google_cloud/myjson.json', scopes)

    service = get_speech_service(credentials)
    service_request = service.speech().asyncrecognize(
        body={
            'config': {
                # There are a bunch of config options you can specify. See
                # https://cloud.google.com/speech/reference/rest/v1beta1/RecognitionConfig for the full list.
                'encoding': 'LINEAR16',  # raw 16-bit signed LE samples
                'sampleRate': 16000,  # 16 khz
                # See http://g.co/cloud/speech/docs/languages 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]

    name = response['name']
    # Construct a GetOperation request.
    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

    # First print the raw json response
    print(json.dumps(response['response'], indent=2))

    # Now print the actual transcriptions
    out = []
    for result in response['response'].get('results', []):
        print 'poo'
        print('Result:')
        for alternative in result['alternatives']:
            print(u'  Alternative: {}'.format(alternative['transcript']))
        out.append(result)
    return response

r = main("/Users/user/Downloads/brooklyn.flac")

Yet my print is the following:

{"name": "3202776140236290963"}
Waiting for server processing...
Waiting for server processing...
{
  "@type": "type.googleapis.com/google.cloud.speech.v1beta1.AsyncRecognizeResponse"
}

And my returned object is:

{u'done': True,
 u'metadata': {u'@type': u'type.googleapis.com/google.cloud.speech.v1beta1.AsyncRecognizeMetadata',
  u'lastUpdateTime': u'2017-03-25T15:54:46.136925Z',
  u'progressPercent': 100,
  u'startTime': u'2017-03-25T15:54:44.514614Z'},
 u'name': u'2024312474309214820',
 u'response': {u'@type': u'type.googleapis.com/google.cloud.speech.v1beta1.AsyncRecognizeResponse'}}

On my console screen I see the requests coming through via:

Unsure why I am not getting the proper transcription back from the sample file.

Any input is appreciated!

Answer 1

Well your config options have the following:

        'config': {
            # There are a bunch of config options you can specify. See
            # https://cloud.google.com/speech/reference/rest/v1beta1/RecognitionConfig for the full list.
            'encoding': 'LINEAR16',  # raw 16-bit signed LE samples
            'sampleRate': 16000,  # 16 khz
            # See http://g.co/cloud/speech/docs/languages for a list of
            # supported languages.
            'languageCode': 'en-US',  # a BCP-47 language tag
        },

However, you are using a FLAC file:

r = main("/Users/user/Downloads/brooklyn.flac")

Quoting https://cloud.google.com/speech/reference/rest/v1beta1/RecognitionConfig:

LINEAR16

Uncompressed 16-bit signed little-endian samples (Linear PCM). This is the only encoding that may be used by speech.asyncrecognize.

FLAC

This is the recommended encoding for speech.syncrecognize and StreamingRecognize because it uses lossless compression; therefore recognition accuracy is not compromised by a lossy codec.

In other words you can't use FLAC with speech.asyncrecognize, you may need to transcode your sample to Linear PCM first, or use speech.syncrecognize with FLAC encoding option.