Google Cloud Speech to Text Operator

前置任務

要使用這些 Operator,您必須完成一些事情

CloudSpeechToTextRecognizeSpeechOperator

識別音訊輸入中的語音並返回文字。

有關引數定義,請參閱 CloudSpeechToTextRecognizeSpeechOperator

引數

config 和 audio 引數需要是 dicts 或來自 google.cloud.speech_v1.types 模組的相應類物件

更多資訊,請參見:https://googleapis.github.io/google-cloud-python/latest/speech/gapic/v1/api.html#google.cloud.speech_v1.SpeechClient.recognize

tests/system/google/cloud/speech_to_text/example_speech_to_text.py

INPUT = {"text": "Sample text for demo purposes"}
VOICE = {"language_code": "en-US", "ssml_gender": "FEMALE"}
AUDIO_CONFIG = {"audio_encoding": "LINEAR16"}

filename 是一個簡單的字串引數

tests/system/google/cloud/speech_to_text/example_speech_to_text.py

CONFIG = RecognitionConfig({"encoding": "LINEAR16", "language_code": "en_US"})
AUDIO = RecognitionAudio({"uri": f"gs://{BUCKET_NAME}/{FILE_NAME}"})

使用 Operator

tests/system/google/cloud/speech_to_text/example_speech_to_text.py

speech_to_text_recognize_task = CloudSpeechToTextRecognizeSpeechOperator(
    config=CONFIG, audio=AUDIO, task_id="speech_to_text_recognize_task"
)

模板化

template_fields: Sequence[str] = (
    "audio",
    "config",
    "project_id",
    "gcp_conn_id",
    "timeout",
    "impersonation_chain",
)

參考

更多資訊,請參閱

此條目是否有幫助?