I have been working on developing a chatbot, for that i would like to consume the above inference model in my application. I have used transformers from hugging face, but not very sure how to consume this model. Please let me know how i can poll this inference model from my application.
Hello 
You can either use a pipeline (if model is hosted on HF and the task has a pipeline) or send a request to the Inference API (again if model is on HF). You can also pull the space and look for how the inference takes place and write the inference part yourself.
Thank you so much for the response merve, Looks like the model is not present in the HuggingFace hub, NATSpeech, portaspeech. How to pull the space and look for inference? could you point to documentation on that?How i can pull the space and use it in my production application?