Serving a TTS model with Seldon In this walkthrough you will learn to serve a multi-part PyTorch model with Seldon. +* +* s2i build . seldonio/seldon-core-s2i-python3:0.10 kubeflow/tts_encoder docker run --name "EncoderServe" --rm -p 5000:5000 kubeflow/tts_encoder