如何在 Python 中接收 Watson Speech to Text SDK 的全部输出？

Question

经过大量测试后，我能够从我在 python 中创建的应用程序接收输出，以使用 IBM bluemix 将语音转换为文本。代码：

import json
from os.path import join, dirname
from ibm_watson import SpeechToTextV1
from ibm_watson.websocket import RecognizeCallback, AudioSource
import threading
from ibm_cloud_sdk_core.authenticators import IAMAuthenticator

authenticator = IAMAuthenticator('xxxx')
service = SpeechToTextV1(authenticator=authenticator)
service.set_service_url('https://api.us-east.speech-to-text.watson.cloud.ibm.com')

models = service.list_models().get_result()
print(json.dumps(models, indent=2))

model = service.get_model('en-US_BroadbandModel').get_result()
print(json.dumps(model, indent=2))

with open(join(dirname('__file__'), 'testvoice3.wav'),
          'rb') as audio_file:
    print(json.dumps(
        service.recognize(
            audio=audio_file,
            content_type='audio/wav',
            timestamps=True,
            word_confidence=True,model='en-US_NarrowbandModel',
        continuous=True).get_result(),
        indent=2))

我收到如下所示的输出：

            [
              "no",
            [
              "their",
              0.41
            ],
            [
              "lives",
              0.1
            ],
            [
              "you",
              0.56
            ],
            [
              "take",
              1.0
            ],
            [
              "Kerr",
              0.95
            ],
            [
              "bye",
              0.4
            ],
            [
              "bye",
              0.99
            ]
          ]
        }
      ],
      "final": true
    }
  ],
  "result_index": 0
}

我只想在一个地方接收整个输出，而不是这种格式。我只想将成绩单与置信度分数分开。所以我可以将其导出到文本文件。我该怎么做？

Answer 1

该输出是单词置信度。输出中应该有一个包含全文的条目，很可能在您的列表中较高的位置。

要将输出压缩为仅转录本，请删除选项 word_confidence=True 和 timestamps=True。

如何在 Python 中接收 Watson Speech to Text SDK 的全部输出？

How do I receive the entire output of the Watson Speech to Text SDK in Python?

python

speech-recognition

ibm-watson