Add API to whisper_playground model service

[MichaelClifford]

Now that we have a whispercpp image that can be used to convert audio to text, want to use it the same way we use the existing playground image, as a model service with an exposed API. Unlike Llama_cpp_python, whisper.cpp does not appear to come with a prebuilt api server for the model. So we should create a light weight API to use for this model type.

[MichaelClifford]

It should follow the openAI API as close as possible https://platform.openai.com/docs/guides/speech-to-text

[MichaelClifford]

Alternatively, we could use the existing example server here in our current image. https://github.com/ggerganov/whisper.cpp/tree/master/examples/server

[MichaelClifford]

closed by #58 and #73