docs: add an example from the last commit on the remaining .onnx files

docs: enhance README and docstrings

refactor: talker, local, lm_head, codec decoder dynamic_axes

docs: add example from the last commit on codec decoder fix

docs: update README related to codec decoder changes

fix: codec decoder input structure and bugs

docs: add example from the last commit

docs: update README regarding model args.

fix: local talker & talker input structure

docs: add an example output for CUDA graph run

fix: bind all inputs for codec decoder

fix: bind all inputs for all talker & local

fix: batched_local_lm_head for CUDA graph

fix: replace `repeat_interleave` GQA talker local

fix: replace `repeat_interleave` on GQA talker

fix: dtype of `inv_freq` to float32 in the init.

fix: make cos and sin for rope as input for talker

fix: make attention_mask as input for talker

fix: onnxruntime install with gpu

docs: add example output after two previous commits

refactor: use one .onnx model for local talker

refactor: use one .onnx model for talker

docs: add cpu example from cuda graph compat. that includes codec decoder

feat: modify codec decoder for cuda graph compat.

docs: add cpu example from refactored cuda graph compat.

refactor: CUDA graph compatibility with IOBinding

docs: remove bugged example

docs: remove bugged example & add the correct ones

fix: mel-spec compute bugs causes wrong identity

feat: add n_iter, codec_decoder, latency log warm-up

feat: add warmup and latency stats

revert: default language and text due to testing

style: format log datetime with ms including to enable with google collab handler

chore: remove unnecessary example args.

Add init. config.json for track

Add files, models, and assets

initial commit