The motivation for this is that setting audio_ctx smaller than the
model default forces the encoder to process shorter chunks than it was
trained on which will hurt accuracy.
In the future a streaming model should be able to handles this instead.
This commit adds a http server for parkeet similar to whisper-server.
The shared functionality has been extracted in to
examples/server-common.h to avoid code duplication.
Daniel Bevenius
Turijon