Zebra Translate
Python Quick Start

Platforms

• Linux (x86_64)
• macOS (x86_64, arm64)
• Windows (x86_64, arm64)
• Raspberry Pi (3, 4, 5)

Requirements

• Picovoice Account & AccessKey
• Python 3.9+
• PIP

Picovoice Account & AccessKey

Signup or Login to Picovoice Console to get your AccessKey. Make sure to keep your AccessKey secret.

Quick Start

Setup

1. Install Python 3.

2. Install the pvzebra Python package using PIP:

pip3 install pvzebra

Usage

Create an instance of the engine and translate text:

import pvzebra

zebra = pvzebra.create(
    access_key="${ACCESS_KEY}", # AccessKey obtained from Picovoice Console (https://console.picovoice.ai/)
    model_path="${MODEL_PATH}", # Replace with a translation model file
)

translation = zebra.translate("${TEXT_TO_TRANSLATE}")

Read more about how to select a model in the Translation Models section.

Free resources used by Zebra Translate:

zebra.delete();

Translation Models

Supported Zebra translation models are located in our GitHub repository. The selected model decides the source and target translation languages.

The format of the model follows:

zebra_params_${SOURCE}_${TARGET}.pv

Where ${SOURCE} is the language code of the source language and ${TARGET} is the language code of the target language for the translation.

Demo

For the Zebra Translate Python SDK, we offer a demo application that demonstrates how to use the Translate engine.

Setup

Install the pvzebrademo Python package using PIP:

pip3 install pvzebrademo

This package installs command-line utilities for the Zebra Translate Python demo.

Usage

Use the --help flag to see the usage options for the demo:

zebra_demo --help

Run the following command to translate text:

zebra_demo --access_key ${ACCESS_KEY} \
           --model_path ${MODEL_PATH} \
           --text ${TEXT_TO_TRANSLATE}

For more information on our Zebra Translate demos for Python, head over to our GitHub repository.

Resources