Google Cloud Speech to Text 運算子¶

先決條件任務¶

若要使用這些運算子，您必須完成以下幾件事

使用 Cloud Console 選取或建立 Cloud Platform 專案。

為您的專案啟用計費功能，詳情請參閱 Google Cloud 文件。

啟用 API，詳情請參閱 Cloud Console 文件。
透過 pip 安裝 API 程式庫。
pip install 'apache-airflow[google]'
如需詳細資訊，請參閱安裝。
設定 Google Cloud 連線.

CloudSpeechToTextRecognizeSpeechOperator¶

辨識音訊輸入中的語音並傳回文字。

如需參數定義，請查看 CloudSpeechToTextRecognizeSpeechOperator

引數¶

config 和 audio 引數需要是字典或 google.cloud.speech_v1.types 模組中對應類別的物件

tests/system/google/cloud/speech_to_text/example_speech_to_text.py[原始碼]

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[原始碼]

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

使用運算子¶

tests/system/google/cloud/speech_to_text/example_speech_to_text.py[原始碼]

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

範本¶

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

參考¶

如需更多資訊，請查看