Add ORTModelXXX for audio (#774)
* add ctc and sequence classification model
* add xvector
* add audio frame classification
* update docstring documentation
* updated docs
* add audio classification test
* update models
* update models
* add audio classification test
* add audio classification test
* add audio classification test
* fixed tests
* fix tests
* updatte model
* rebase
* update test
* fix test
* fixed tests
* update docs
* fix code docstring
* update docs
* add numpy tests
* add error for iobinding
* update docs
* update docs
---------
Co-authored-by: Mohit Sharma <mohit@huggingface.co>
