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
8250a79b23
Implemented kv_cache "fix" (from 1f3c1b5f4a); guess I should find out why it's crashing DirectML backend
2023-02-13 13:48:31 +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
52a9ed7858
Moved voices out of the tortoise folder because it kept being processed for setup.py
2023-02-10 20:11:56 +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
729be135ef
Added option: listen path
2023-02-09 20:42:38 +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
319e7ec0a6
fixed up the computing conditional latents
2023-02-06 03:44:34 +00:00
b23f583c4e
Forgot to rename the cached latents to the new filename
2023-02-05 23:51:52 +00:00
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
4ea997106e
oops
2023-02-05 20:10:40 +00:00
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
7b767e1442
New tunable: pause size/breathing room (governs pause at the end of clips)
2023-02-05 14:45:51 +00:00
f38c479e9b
Added multi-line parsing
2023-02-05 06:17:51 +00:00
111c45b181
Set transformer and model folder to local './models/' instead of for the user profile, because I'm sick of more bloat polluting my C:\
2023-02-05 04:18:35 +00:00
078dc0c6e2
Added choices to choose between diffusion samplers (p, ddim)
2023-02-05 01:28:31 +00:00
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
061aa65ac4
Reverted slight improvement patch, as it's just enough to OOM on GPUs with low VRAM
2023-02-03 21:45:06 +00:00
4f359bffa4
Added progress for transforming to audio, changed number inputs to sliders instead
2023-02-03 04:56:30 +00:00
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
1eb92a1236
QoL fixes
2023-02-02 21:13:28 +00:00
James Betker
aad67d0e78
Merge pull request #233 from kianmeng/fix-typos
...
Fix typos
2023-01-17 18:24:24 -07:00
원빈 정
092b15eded
Add reference of univnet implementation
2023-01-06 15:57:02 +09:00
Kian-Meng Ang
49bbdd597e
Fix typos
...
Found via `codespell -S *.json -L splitted,nd,ser,broadcat`
2023-01-06 11:04:36 +08:00
James Betker
e5201bf14e
Get rid of checkpointing
...
It isn't needed in inference.
2022-06-15 22:09:15 -06:00
Johan Nordberg
dba14650cb
Typofix
2022-06-11 21:19:07 +09:00
Johan Nordberg
5c7a50820c
Allow running on CPU
2022-06-11 20:03:14 +09:00
Marcus Llewellyn
0e08760896
Fixed silly lack of EOF blank line, indentation
2022-06-06 15:13:29 -05:00
Marcus Llewellyn
5a74461c1e
read.py combines all candidates
...
If candidates where greater than 1 on in read.py, only the fist candidate clips would be combined. This adds a bit of code to make a combined file for every candidate.
2022-06-04 17:47:29 -05:00
James Betker
ce30b5bbe5
Merge pull request #74 from jnordberg/improved-cli
...
Add CLI tool
2022-05-28 21:33:53 -06:00
Johan Nordberg
491fe7f6d3
Remove some assumptions about working directory
...
This allows cli tool to run when not standing in repository dir
2022-05-29 01:10:19 +00:00
Johan Nordberg
a641d8f29b
Add tortoise_cli.py
2022-05-28 05:25:23 +00:00
Johan Nordberg
821be4171b
Typofix
2022-05-28 01:29:34 +00:00
Johan Nordberg
069e7001ad
Improve splitting on text that has many quotes
2022-05-28 01:22:21 +00:00
Johan Nordberg
cf26074fa5
Add riding hood test
...
Also fix a bug discovered by the test that would seek past the text end if it ended in a boundary
2022-05-27 23:08:53 +00:00
Johan Nordberg
acc0891e85
Improve sentence boundary detection
2022-05-27 05:58:09 +00:00
Josh Ziegler
53f6563e3e
avoid mutable default in aligner
2022-05-26 16:20:09 -04:00
Johan Nordberg
f396dcc023
Skip CLVP if cvvp_amount is 1
...
Also fixes formatting bug in log message
2022-05-25 11:12:53 +00:00
Johan Nordberg
0ca4d8f291
Revive CVVP model
2022-05-25 10:22:50 +00:00
James Betker
e0be49f02f
Fix bug
2022-05-22 05:50:26 -06:00
James Betker
42a3bc9cfd
Support combining voices in do_tts
2022-05-22 05:28:15 -06:00
James Betker
412315ab7d
Update read.py to support multiple candidates
2022-05-22 05:26:01 -06:00
James Betker
d96d55a8b4
Fix faulty merge
2022-05-19 10:37:57 -06:00
James Betker
a1c131bde9
Merge remote-tracking branch 'origin/main'
...
# Conflicts:
# tortoise/read.py
2022-05-19 10:34:54 -06:00
Johan Nordberg
b4fa8c86b9
Allow passing additional voice directories when loading voices
2022-05-19 21:02:11 +09:00
Johan Nordberg
00730d2786
Allow setting models path from environment variable
2022-05-19 21:02:09 +09:00
James Betker
8fdf516e62
Remove CVVP
...
After training a similar model for a different purpose, I realized that
this model is faulty: the contrastive loss it uses only pays attention
to high-frequency details which do not contribute meaningfully to
output quality. I validated this by comparing a no-CVVP output with
a baseline using tts-scores and found no differences.
2022-05-17 12:21:25 -06:00
James Betker
a1ae84c49d
Add a way to get deterministic behavior from tortoise and add debug states for reporting
2022-05-17 12:11:18 -06:00
James Betker
93d0ce60d3
Merge remote-tracking branch 'origin/main'
2022-05-17 11:22:40 -06:00
James Betker
5d611aff8c
Add chapter 1 of GoT for read.py demos
2022-05-17 11:21:57 -06:00
Danila Berezin
ef5fb5f5fc
Fix bug in load_voices in audio.py
...
The read.py script did not work with pth latents, so I fix bug in audio.py. It seems that in the elif statement, instead of voice, voices should be clip, clips. And torch stack doesn't work with tuples, so I had to split this operation.
2022-05-17 18:34:54 +03:00
James Betker
e0329de2c2
Merge pull request #42 from jnordberg/main
...
Improve sentence splitting
2022-05-14 08:52:46 -06:00
James Betker
0570034eda
Automatically pick batch size based on available GPU memory
2022-05-13 10:30:02 -06:00
Johan Nordberg
a8fa71b82d
Improve sentence splitting
2022-05-13 11:02:17 +00:00
James Betker
b3b36c0041
update model paths (including clvp2!)
2022-05-12 20:18:11 -06:00
James Betker
f5ebd14d09
Add error message
2022-05-12 20:15:40 -06:00
James Betker
c4a5a23985
add eval script for testing
2022-05-12 20:15:22 -06:00
James Betker
44a4419348
CLVP2!
2022-05-12 13:23:03 -06:00
James Betker
fc7b308e3b
Add support for multiple output candidates in do_tts.
2022-05-12 11:25:35 -06:00
James Betker
33d4226a7d
read.py: allow user-specified splits
2022-05-12 11:24:55 -06:00
Mark Baushenko
cc38333249
Optimizing graphics card memory
...
During inference it does not store gradients, which take up most of the video memory
2022-05-11 16:35:11 +03:00
James Betker
e4e9523900
re-enable redaction
2022-05-06 09:36:42 -06:00
James Betker
9151650559
temporarily disable redaction
2022-05-06 09:06:20 -06:00
James Betker
e18428166d
v2.2
2022-05-06 00:11:10 -06:00
James Betker
4704eb1cef
Update readme with prompt engineering
2022-05-03 21:32:06 -06:00
James Betker
b11f6ddd60
Enable redaction by default
2022-05-03 21:21:52 -06:00
James Betker
53cb3299d4
change quality presets
2022-05-03 21:01:26 -06:00
James Betker
e23e6f6696
Use librosa for loading mp3s
2022-05-03 20:44:31 -06:00
James Betker
dc0390ade1
Remove entmax dep
2022-05-02 21:43:14 -06:00
James Betker
12acac6f77
Fix default output path
2022-05-02 21:37:39 -06:00
James Betker
022d330300
k I think this works..
2022-05-02 21:31:31 -06:00
James Betker
00e84bbd86
fix paths
2022-05-02 20:56:28 -06:00
James Betker
e4e8ebfc55
getting ready for 2.1 release
2022-05-02 20:20:50 -06:00
James Betker
5663e98904
misc fixes
2022-05-02 18:00:57 -06:00
James Betker
e00606a601
Fix bug with k>1
2022-05-02 18:00:22 -06:00
James Betker
ccf16f978e
more fixes
2022-05-02 16:44:47 -06:00
James Betker
4836e1f792
fix warning
2022-05-02 16:36:02 -06:00
James Betker
ee24d3ee4b
Support totally random voices (and make fixes to previous changes)
2022-05-02 15:40:03 -06:00
James Betker
a57fcaf814
move data
2022-05-02 15:39:34 -06:00
James Betker
f631123264
Add redaction support
2022-05-02 14:57:29 -06:00
James Betker
f823e31e49
Better error messages when inputs are out of bounds.
2022-05-01 17:39:36 -06:00
James Betker
66805da4bd
add support for specifying the model_dir
2022-05-01 17:29:25 -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
98070eeb32
more cleanup
2022-05-01 16:28:39 -06:00
