28 Commits

Author	SHA1	Message	Date
mrq	94eab20529	disable telemetry/what-have-you if not requesting a public Gradio URL	2023-02-07 21:44:16 +00:00
mrq	e45e4431d1	(finally) added the CVVP model weigh slider, latents export more data too for weighing against CVVP	2023-02-07 20:55:56 +00:00
mrq	f7274112c3	un-hardcoded input output sampling rates (changing them "works" but leads to wrong audio, naturally)	2023-02-07 18:34:29 +00:00
mrq	55058675d2	(maybe) fixed an issue with using prompt redactions (emotions) on CPU causing a crash, because for some reason the wav2vec_alignment assumed CUDA was always available	2023-02-07 07:51:05 -06:00
mrq	5d76d47a49	added shell scripts for linux, wrapped sorted() for voice list, I guess	2023-02-06 21:54:31 -06:00
mrq	3b56c437aa	fixed combining audio, somehow this broke, oops	2023-02-07 00:26:22 +00:00
mrq	a3c077ba13	added setting to adjust autoregressive sample batch size	2023-02-06 22:31:06 +00:00
mrq	d8c88078f3	Added settings page, added checking for updates (disabled by default), some other things that I don't remember	2023-02-06 21:43:01 +00:00
mrq	d1172ead36	Added encoding and ripping latents used to generate the voice	2023-02-06 16:32:09 +00:00
mrq	e25ec325fe	Added tab to read and copy settings from a voice clip (in the future, I'll see about enmbedding the latent used to generate the voice)	2023-02-06 16:00:44 +00:00
mrq	edb6a173d3	added another (somewhat adequate) example, added metadata storage to generated files (need to add in a viewer later)	2023-02-06 14:17:41 +00:00
mrq	b8b15d827d	added flag (--cond-latent-max-chunk-size) that should restrict the maximum chunk size when chunking for calculating conditional latents, to avoid OOMing on VRAM	2023-02-06 05:10:07 +00:00
mrq	b23f583c4e	Forgot to rename the cached latents to the new filename	2023-02-05 23:51:52 +00:00
mrq	c2c9b1b683	modified how conditional latents are computed (before, it just happened to only bother reading the first 102400/24000=4.26 seconds per audio input, now it will chunk it all to compute latents)	2023-02-05 23:25:41 +00:00
mrq	daebc6c21c	added button to refresh voice list, enabling KV caching for a bonerific speed increase (credit to https://github.com/152334H/tortoise-tts-fast/)	2023-02-05 17:59:13 +00:00
mrq	7b767e1442	New tunable: pause size/breathing room (governs pause at the end of clips)	2023-02-05 14:45:51 +00:00
mrq	ec31d1763a	Fix to keep prompted emotion for every split line	2023-02-05 06:55:09 +00:00
mrq	98dbf56d44	Skip combining if not splitting, also avoids reading back the audio files to combine them by keeping them in memory	2023-02-05 06:35:32 +00:00
mrq	f38c479e9b	Added multi-line parsing	2023-02-05 06:17:51 +00:00
mrq	3e3634f36a	Fixed accidentally not passing user-provided samples/iteration values (oops), fixed error thrown when trying to write unicode because python sucks	2023-02-05 05:51:57 +00:00
mrq	26daca3dc6	Forgot to add steps=1 to Candidates slider	2023-02-05 04:27:20 +00:00
mrq	d2aeadd754	cleaned up element order with Blocks, also added preset updating the samples/iterations counts	2023-02-05 03:53:46 +00:00
mrq	078dc0c6e2	Added choices to choose between diffusion samplers (p, ddim)	2023-02-05 01:28:31 +00:00
mrq	4274cce218	Added small optimization with caching latents, dropped Anaconda for just a py3.9 + pip + venv setup, added helper install scripts for such, cleaned up app.py, added flag '--low-vram' to disable minor optimizations	2023-02-04 01:50:57 +00:00
mrq	4f359bffa4	Added progress for transforming to audio, changed number inputs to sliders instead	2023-02-03 04:56:30 +00:00
mrq	ef237c70d0	forgot to copy the alleged slight performance improvement patch, added detailed progress information with passing gr.Progress, save a little more info with output	2023-02-03 04:20:01 +00:00
mrq	aafef3a140	Cleaned up the good-morning-sirs-dialect labels, fixed seed=0 not being a random seed, show seed on output	2023-02-03 01:25:03 +00:00
mrq	1eb92a1236	QoL fixes	2023-02-02 21:13:28 +00:00