|
|
cbd3c95c42
|
possible speedup with one simple trick (it worked for valle inferencing), also backported the voice list loading from aivc
|
2023-08-20 22:32:01 -05:00 |
|
|
|
9afa71542b
|
little sloppy hack to try and not load the same model when it was already loaded
|
2023-08-11 04:02:36 +00:00 |
|
|
|
5ff00bf3bf
|
added flags to rever to default method of latent generation (separately for the AR and Diffusion latents, as some voices don't play nicely with the chunk-for-all method)
|
2023-05-21 01:46:55 +00:00 |
|
|
|
c90ee7c529
|
removed kludgy wrappers for passing progress when I was a pythonlet and didn't know gradio can hook into tqdm outputs anyways
|
2023-05-04 23:39:39 +00:00 |
|
|
|
086aad5b49
|
quick hotfix to remove offending codesmell (will actually clean it when I finish eating)
|
2023-05-04 22:59:57 +00:00 |
|
|
|
0bcdf81d04
|
option to decouple sample batch size from CLVP candidate selection size (currently just unsqueezes the batches)
|
2023-03-21 21:33:46 +00:00 |
|
|
|
e201746eeb
|
added diffusion_model and tokenizer_json as arguments for settings editing
|
2023-03-16 14:19:24 +00:00 |
|
|
|
42cb1f3674
|
added args for tokenizer and diffusion model (so I don't have to add it later)
|
2023-03-15 00:30:28 +00:00 |
|
|
|
65a43deb9e
|
why didn't I also have it use chunks for computing the AR conditional latents (instead of just the diffusion aspect)
|
2023-03-14 01:13:49 +00:00 |
|
|
|
97cd58e7eb
|
maybe solved that odd VRAM spike when doing the clvp pass
|
2023-03-12 12:48:29 -05:00 |
|
|
|
fffea7fc03
|
unmarried the config.json to the bigvgan by downloading the right one
|
2023-03-07 13:37:45 +00:00 |
|
|
|
26133c2031
|
do not reload AR/vocoder if already loaded
|
2023-03-07 04:33:49 +00:00 |
|
|
|
e2db36af60
|
added loading vocoders on the fly
|
2023-03-07 02:44:09 +00:00 |
|
|
|
7b2aa51abc
|
oops
|
2023-03-06 21:32:20 +00:00 |
|
|
|
7f98727ad5
|
added option to specify autoregressive model at tts generation time (for a spicy feature later)
|
2023-03-06 20:31:19 +00:00 |
|
|
|
6fcd8c604f
|
moved bigvgan model to a huggingspace repo
|
2023-03-05 19:47:22 +00:00 |
|
|
|
06bdf72b89
|
load the model on CPU because torch doesn't like loading models directly to GPU (it just follows the default vocoder loading behavior)
|
2023-03-03 13:53:21 +00:00 |
|
|
|
2ba0e056cd
|
attribution
|
2023-03-03 06:45:35 +00:00 |
|
|
|
aca32a71f7
|
added BigVGAN in place of default vocoder (credit to https://github.com/deviandice/tortoise-tts-BigVGAN)
|
2023-03-03 06:30:58 +00:00 |
|
|
|
a9de016230
|
added storing the loaded model's hash to the TTS object instead of relying on jerryrig injecting it (although I still have to for the weirdos who refuse to update the right way), added a parameter when loading voices to load a latent tagged with a model's hash so latents are per-model now
|
2023-03-02 00:44:42 +00:00 |
|
|
|
7b839a4263
|
applied the bitsandbytes wrapper to tortoise inference (not sure if it matters)
|
2023-02-28 01:42:10 +00:00 |
|
|
|
7cc0250a1a
|
added more kill checks, since it only actually did it for the first iteration of a loop
|
2023-02-24 23:10:04 +00:00 |
|
|
|
34b232927e
|
Oops
|
2023-02-19 01:54:21 +00:00 |
|
|
|
d8c6739820
|
added constructor argument and function to load a user-specified autoregressive model
|
2023-02-18 14:08:45 +00:00 |
|
|
|
6ad3477bfd
|
one more update
|
2023-02-16 23:18:02 +00:00 |
|
|
|
30298b9ca3
|
fixing brain worms
|
2023-02-16 21:36:49 +00:00 |
|
|
|
ea1bc770aa
|
added option: force cpu for conditioning latents, for when you want low chunk counts but your GPU keeps OOMing because fuck fragmentation
|
2023-02-15 05:01:40 +00:00 |
|
|
|
2e777e8a67
|
done away with kludgy shit code, just have the user decide how many chunks to slice concat'd samples to (since it actually does improve vocie replicability)
|
2023-02-15 04:39:31 +00:00 |
|
|
|
0bc2c1f540
|
updates chunk size to the chunked tensor length, just in case
|
2023-02-14 17:13:34 +00:00 |
|
|
|
48275899e8
|
added flag to enable/disable voicefixer using CUDA because I'll OOM on my 2060, changed from naively subdividing eavenly (2,4,8,16 pieces) to just incrementing by 1 (1,2,3,4) when trying to subdivide within constraints of the max chunk size for computing voice latents
|
2023-02-14 16:47:34 +00:00 |
|
|
|
b648186691
|
history tab doesn't naively reuse the voice dir instead for results, experimental "divide total sound size until it fits under requests max chunk size" doesn't have a +1 to mess things up (need to re-evaluate how I want to calculate sizes of bests fits eventually)
|
2023-02-14 16:23:04 +00:00 |
|
|
|
5b5e32338c
|
DirectML: fixed redaction/aligner by forcing it to stay on CPU
|
2023-02-12 20:52:04 +00:00 |
|
|
|
4d01bbd429
|
added button to recalculate voice latents, added experimental switch for computing voice latents
|
2023-02-12 18:11:40 +00:00 |
|
|
|
88529fda43
|
fixed regression with computing conditional latencies outside of the CPU
|
2023-02-12 17:44:39 +00:00 |
|
|
|
65f74692a0
|
fixed silently crashing from enabling kv_cache-ing if using the DirectML backend, throw an error when reading a generated audio file that does not have any embedded metadata in it, cleaned up the blocks of code that would DMA/transfer tensors/models between GPU and CPU
|
2023-02-12 14:46:21 +00:00 |
|
|
|
1b55730e67
|
fixed regression where the auto_conds do not move to the GPU and causes a problem during CVVP compare pass
|
2023-02-11 20:34:12 +00:00 |
|
|
|
a7330164ab
|
Added integration for "voicefixer", fixed issue where candidates>1 and lines>1 only outputs the last combined candidate, numbered step for each generation in progress, output time per generation step
|
2023-02-11 15:02:11 +00:00 |
|
|
|
4f903159ee
|
revamped result formatting, added "kludgy" stop button
|
2023-02-10 22:12:37 +00:00 |
|
|
|
efa556b793
|
Added new options: "Output Sample Rate", "Output Volume", and documentation
|
2023-02-10 03:02:09 +00:00 |
|
|
|
57af25c6c0
|
oops
|
2023-02-09 22:17:57 +00:00 |
|
|
|
504db0d1ac
|
Added 'Only Load Models Locally' setting
|
2023-02-09 22:06:55 +00:00 |
|
|
|
3f8302a680
|
I didn't have to suck off a wizard for DirectML support (courtesy of https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/7600 for leading the way)
|
2023-02-09 05:05:21 +00:00 |
|
|
|
b23d6b4b4c
|
owari da...
|
2023-02-09 01:53:25 +00:00 |
|
|
|
494f3c84a1
|
beginning to add DirectML support
|
2023-02-08 23:03:52 +00:00 |
|
|
|
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 |
|
|
|
f7274112c3
|
un-hardcoded input output sampling rates (changing them "works" but leads to wrong audio, naturally)
|
2023-02-07 18:34:29 +00:00 |
|
|
|
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 |
|
|
|
328deeddae
|
forgot to auto compute batch size again if set to 0
|
2023-02-06 23:14:17 -06:00 |
|
|
|
a3c077ba13
|
added setting to adjust autoregressive sample batch size
|
2023-02-06 22:31:06 +00:00 |
|
|
|
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 |
|
