Google Cloud Speech Translate Operators¶
Prerequisite Tasks¶
To use these operators, you must do a few things:
Select or create a Cloud Platform project using Cloud Console.
Enable billing for your project, as described in Google Cloud documentation.
Enable API, as described in Cloud Console documentation.
Install API libraries via pip.
pip install 'apache-airflow[gcp]'
Detailed information is available Installation
GcpTranslateSpeechOperator¶
Recognizes speech in audio input and translates it.
For parameter definition, take a look at
airflow.contrib.operators.gcp_translate_speech_operator.GcpTranslateSpeechOperator
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
CONFIG = {"encoding": "LINEAR16", "language_code": "en_US"}
AUDIO = {"uri": "gs://{bucket}/{object}".format(bucket=BUCKET_NAME, object=FILENAME)}
Arguments for translation need to be specified.
TARGET_LANGUAGE = 'pl'
FORMAT = 'text'
MODEL = 'base'
SOURCE_LANGUAGE = None
Using the operator¶
translate_speech_task = GcpTranslateSpeechOperator(
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'
)
Templating¶
template_fields = ('target_language', 'format_', 'source_language', 'model', 'project_id', 'gcp_conn_id')