How to deploy a Text to Speech model on AWS

I’m trying to deploy my Trained Text to speech model using AWS lambda services but as I haven’t worked on the deployment part before so I’m having trouble to figure out the initial steps. My model consist of two trained models one is waveglow for inferencing and the other one is my trained tacotron2 model on a specific language. I know how to create a lambda function and trigger s3 bucket in which my model is saved but cant figure out how to define a lambda function. Please guide me with the process. Thanks in advance.

Hey, did you ever solve your problem? Which tutorial or options did you try? I’m curious if you tried using sagemaker for model hosting since you’re already on AWS, such as described here: Deploy a Trained PyTorch Model — Amazon SageMaker Examples 1.0.0 documentation.