Google Cloud Speech Translate Operators¶

Prerequisite Tasks¶

CloudTranslateSpeechOperator¶

Recognizes speech in audio input and translates it.

For parameter definition, take a look at CloudTranslateSpeechOperator

Arguments¶

Config and audio arguments need to be dicts or objects of corresponding classes from google.cloud.speech_v1.types module.

for more information, see: https://googleapis.github.io/google-cloud-python/latest/speech/gapic/v1/api.html#google.cloud.speech_v1.SpeechClient.recognize

Arguments for translation need to be specified.

airflow/providers/google/cloud/example_dags/example_translate_speech.pyView Source

CONFIG = {"encoding": "LINEAR16", "language_code": "en_US"}
AUDIO = {"uri": f"gs://{BUCKET_NAME}/{FILENAME}"}
TARGET_LANGUAGE = 'pl'
FORMAT = 'text'
MODEL = 'base'
SOURCE_LANGUAGE = None  # type: None

Using the operator¶

airflow/providers/google/cloud/example_dags/example_translate_speech.pyView Source

translate_speech_task = CloudTranslateSpeechOperator(
    project_id=GCP_PROJECT_ID,
    audio=AUDIO,
    config=CONFIG,
    target_language=TARGET_LANGUAGE,
    format_=FORMAT,
    source_language=SOURCE_LANGUAGE,
    model=MODEL,
    task_id='translate_speech_task',
)
translate_speech_task2 = CloudTranslateSpeechOperator(
    audio=AUDIO,
    config=CONFIG,
    target_language=TARGET_LANGUAGE,
    format_=FORMAT,
    source_language=SOURCE_LANGUAGE,
    model=MODEL,
    task_id='translate_speech_task2',
)

Templating¶

template_fields = (
    'target_language',
    'format_',
    'source_language',
    'model',
    'project_id',
    'gcp_conn_id',
    'impersonation_chain',
)

Reference¶

For further information, look at: