Chunked inference for codec (#22)

* Adding some devtools.

* Adding delay calculation

* Chunked inference for codec.

* Version bump

* Removing prod.yml, updating to recent main.

* Turning padding off only when chunking codes.

* Updating README, removing unused things.

* Missed a padding.

* Adding some checks to make sure pads are the same.

* Factoring out latent dim, backwards compatible.

* Adding latent dim, and the 44khz 16kbps model config.

* Ran pre-commit.

* Chunked vs unchunked inference.

* Fixing padding stuff.

* n quantizers back in encode

* don't load unsupported versions

* correct docstring

* bitrate config + 16kbps models

* update audiotools dep

* fix argbind issue

* minor correction

* bump version

* change model path

* update audiotools deps

---------

Co-authored-by: prem <prem@descript.com>
Co-authored-by: Ishaan Kumar <ishaan@descript.com>

Add final training configs as well as release 16 KHz model (#19)

* adding final configs for all models

* changs for 16khz

* add latest version for 16khz model

* update package version

---------

Co-authored-by: Ishaan Kumar <ishaan@descript.com>

24kHz model release (#13)

* add support for multiple models

* expose model_type arg to cli + docs update

* version updates

* update tests

* expose download args via cli

* doc correction

* minor change

* update readme

* minor change

Use n_quantizers and save codes as uint16 (#12)

* restrict full quantizer usage during inference

* save/load uint16 codes

* add test

* bump version

change package name (#7)

Prepare code for public release