Generalising static quantization implementation of Calibrationdatareader for quantization for different architectures

[manickavela29]

Currently working with Zipformer2 (based on conformers) models from icefall, the model has its input states from previous inference output(except for first inference as all are zeros).
Zipformer is a Transformer based ASR model, with major compute ops of Matmul and Conv(depth and pointwise)

Model : Zipformer2
Inputs : X(feature vector), and States -> a list of 96 states(initialised as 0).
output: Y, and list of 96 states (these output states are maintained separately and fed as input for next output)

Current implementation for Static Quantization function quant_static() takes in fp32 model and calibrationdatsetreader
and does the quantization but, this implementation does not support models like zip formers where in input and output are dependent on states