使用 Google Speech 时从 Google Cloud Storage 访问音频文件

Question

我已使用下面的这段代码成功地使用 Google Speech 将包含语音的 .wav 文件解析为文本。

但我想访问一个不同的 .wav 文件，该文件已（公开）放置在 Google Cloud Storage 上，而不是本地硬盘上。为什么不简单地改变

speech_file = 'my/local/system/sample.wav'

到
speech_file = 'https://console.cloud.google.com/storage/browser/speech_proj_files/sample.wav'

工作可以接受吗？

这是我的代码：

speech_file = 'https://console.cloud.google.com/storage/browser/speech_proj_files/sample.wav'

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


def get_speech_service():
    credentials = GoogleCredentials.get_application_default().create_scoped(
        ['https://www.googleapis.com/auth/cloud-platform'])
    http = htt|plib2.Http()
    credentials.authorize(http)

    return discovery.build(
        'speech', 'v1beta1', http=http, discoveryServiceUrl=DISCOVERY_URL)

def main(speech_file):
    """Transcribe the given audio file.

    Args:
        speech_file: the name of the audio file.
    """
    with open(speech_file, 'rb') as speech:
        speech_content = base64.b64encode(speech.read())

    service = get_speech_service()
    service_request = service.speech().syncrecognize(
        body={
            'config': {
                'encoding': 'LINEAR16',  # raw 16-bit signed LE samples
                'sampleRate': 44100,  # 16 khz
                'languageCode': 'en-US',  # a BCP-47 language tag
            },
            'audio': {
                'content': speech_content.decode('UTF-8')
                }
            })
    response = service_request.execute()
    return response

Answer 1

我不确定为什么您的方法不起作用，但我想提供一个快速建议。

Google Cloud Speech API 原生支持 Google Cloud Storage 对象。无需下载整个对象并将其上传回 Cloud Speech API，只需通过替换此行来指定对象：

        'audio': {
            # Remove this: 'content': speech_content.decode('UTF-8')
            'uri': 'gs://speech_proj_files/sample.wav'  # Do this!
            }

另一个建议。您可能会发现google-cloud Python 库更易于使用。试试这个：

from google.cloud import speech
speech_client = speech.Client()

audio_sample = speech_client.sample(
    content=None,
    source_uri='gs://speech_proj_files/sample.wav',
    encoding='LINEAR16',
    sample_rate_hertz= 44100)
results_list = audio_sample.sync_recognize(language_code='en-US')

这里有一些很好的例子：https://github.com/GoogleCloudPlatform/python-docs-samples/tree/master/speech/cloud-client