new voices

Remove intelligibility refinement

Update sweep & eval_multiple with new voices

support latents into the diffusion decoder

Updates

support presets for generation

Add read script

Clip diffusion inputs

Updates

updates for new autoregressive

new autoregressive check-in

integrate new autoregressive model and fix new diffusion bug

Integrate new diffusion network

port do_tts to use the API

param improvements from investigation

Add sweeper script for finding optimal generation hyperparameters.

Update API to have more expressive interface for controlling various generation knobs

Upgrade CLIP model and add eval_multiple

Add in ASR filtration

Modifications to support "v1.5"

Another update

Update readme

More updates

Add colab notebook

Some fixes

Update with downloadable model paths

Upload sample results and voices

Update docs

Some renaming

Initial commit

Initial commit