Watson语音到文本API中，扬声器标签/偏音不返回

Question

[我正在尝试通过IBM Watson语音获取发短信给标签的标签。在我的最终输出中，我希望它显示整个音频的笔录，自信心和说话者标签。我的代码如下：

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
import pandas as pd
authenticator = IAMAuthenticator('rXXXYYZZ')
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__'), 'testvoicejen.wav'),
          'rb') as audio_file:
#    print(json.dumps(
    output = service.recognize(
    audio=audio_file,
    speaker_labels=True,
    content_type='audio/wav',
    #timestamps=True,
    #word_confidence=True,
    model='en-US_NarrowbandModel',
    continuous=True).get_result(),
    indent=2
df = pd.DataFrame([i for elts in output for alts in elts['results'] for i in alts['alternatives']])

但是，df的输出是：

df
Out[22]: 
                                          timestamps  ...                                         transcript
0  [[thank, 3.88, 4.04], [you, 4.04, 4.13], [for,...  ...  thank you for calling my name is Britney and h...
1  [[thank, 30.21, 30.56], [you, 30.56, 30.74], [...  ...  thank you %HESITATION and then %HESITATION you..

您可以看到，我确实获得了成绩单，但是，我得到了时间戳，而不是说话人的二字化或标签化。演讲者标签如下所示：

from": 0.68,
      "to": 1.19,
      "speaker": 2

我怎么得到这个？

Answer 1

打开speaker_labels时，会自动获得timestamps。如果查看示例输出-https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-output#speaker_labels

您将看到扬声器标签部分与替代部分分开。您的代码仅解析“替代”部分。如果您想要扬声器标签，将为：

df = pd.DataFrame([i for elts in output for spk in elts['results'] for i in spk['speaker_labels']])