James Betker 0ffc191408 Add support for extracting and feeding conditioning latents directly into the model ... - Adds a new script and API endpoints for doing this - Reworks autoregressive and diffusion models so that the conditioning is computed separately (which will actually provide a mild performance boost) - Updates README This is untested. Need to do the following manual tests (and someday write unit tests for this behemoth before it becomes a problem..) 1) Does get_conditioning_latents.py work? 2) Can I feed those latents back into the model by creating a new voice? 3) Can I still mix and match voices (both with conditioning latents and normal voices) with read.py?		2022-05-01 17:25:18 -06:00
..
__init__.py	Move everything into the tortoise/ subdirectory	2022-05-01 16:24:24 -06:00
audio.py	Add support for extracting and feeding conditioning latents directly into the model	2022-05-01 17:25:18 -06:00
diffusion.py	Move everything into the tortoise/ subdirectory	2022-05-01 16:24:24 -06:00
samples_generator.py	more cleanup	2022-05-01 16:28:39 -06:00
stft.py	Move everything into the tortoise/ subdirectory	2022-05-01 16:24:24 -06:00
tokenizer.py	Move everything into the tortoise/ subdirectory	2022-05-01 16:24:24 -06:00
typical_sampling.py	Move everything into the tortoise/ subdirectory	2022-05-01 16:24:24 -06:00