Fix a error while following tutorial 1

[cyun9601]

When following the tutorial from the link below:

https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/tutorials/Conceptual_Guide/Part_1-model_deployment/README.html#launching-the-server

an error occurs in the config.pbtxt for text_recognition:

"failed to load 'text_recognition' version 1: Invalid argument: unexpected inference output '308', allowed outputs are: 307"

Update config.pbtxt

[cyun9601]

It is works for now using 308