17 Commits

Author	SHA1	Message	Date
James Betker	4704eb1cef	Update readme with prompt engineering	2022-05-03 21:32:06 -06:00
James Betker	958b939b64	Add setup	2022-05-02 21:24:34 -06:00
James Betker	19f38f454f	Update README and update to version 2.1	2022-05-02 21:02:29 -06:00
James Betker	e4e8ebfc55	getting ready for 2.1 release	2022-05-02 20:20:50 -06:00
James Betker	01b783fc02	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
James Betker	e8966d09cf	ack	2022-04-27 23:22:55 -06:00
James Betker	5bd6f0fb9c	tortoise-detect docs	2022-04-26 10:37:44 -06:00
James Betker	ad2419f31d	updates	2022-04-25 21:28:18 -06:00
James Betker	e962c9bad7	update readme	2022-04-25 21:19:02 -06:00
James Betker	d96d2bd76e	add regenerate option	2022-04-25 20:05:21 -06:00
James Betker	e877af5b0f	update	2022-04-25 17:02:59 -06:00
James Betker	a3daadd121	Update documentation, add optional verbosity	2022-04-25 16:59:04 -06:00
James Betker	9f1aa57b8d	Another update	2022-03-10 23:33:48 -07:00
James Betker	f36bb6006d	Update readme	2022-03-10 23:32:35 -07:00
James Betker	16f5d4f625	Update docs	2022-02-03 22:18:21 -07:00
James Betker	e16ab82597	Initial commit	2022-01-27 23:19:29 -07:00
James Betker	e52926391c	Initial commit	2022-01-27 21:33:15 -07:00