Revert "Merge pull request #3 from osanseviero/main"

Package everything

move voices

updates to scripts

yeah

update do_tts

update

Add read script

integrate new autoregressive model and fix new diffusion bug

port do_tts to use the API

Upgrade CLIP model and add eval_multiple

Add in ASR filtration

Modifications to support "v1.5"

More updates

Some fixes

Update with downloadable model paths

Update docs

Some renaming

Initial commit