DEV Community

Cover image for Google T5 Translation as a Service with Just 7 lines of Codes
wjiuhe
wjiuhe

Posted on

Google T5 Translation as a Service with Just 7 lines of Codes

What is T5? Text-To-Text Transfer Transformer (T5) from Google gives the power of translation.

translation

In the article, we will deploy Google T5 model as a REST API service. Difficult? What about I’ll tell you: you just need to write 7 lines of codes?

translation

**HuggingFace** makes it easy to use the pretrained model with just several lines.

**Pinferencia** makes it super easy to serve any model with just three extra lines.

translation

Install Dependencies

HuggingFace

pip install "transformers[pytorch]"

If it doesn’t work, please visit Installation (huggingface.co) and check their official documentations.

Pinferencia

pip install "pinferencia[uvicorn]"

If it doesn’t work, please visit Install — Pinferencia (underneathall.app) and check their official documentations.

Define the Service

First let’s create the app.py to define the service:

Start the Service

uvicorn app:service --reload
Enter fullscreen mode Exit fullscreen mode

Wait for the model get downloaded. When it’s finished, you’ll see:

finished

Call the Service

You can use curl or the interactive api page from Pinferencia.

Curl

curl

The result:

result

Interactive API Page

api page

Result:

result

If you like Pinferencia don’t forget to go to GitHub and save to your favorites.

Discussion (0)