409dec98d5
fixed voicefixing not working as intended, load TTS before Gradio in the webui due to how long it takes to initialize tortoise (instead of just having a block to preload it)
2023-02-12 20:05:59 +00:00
b85c9921d7
added button to recalculate voice latents, added experimental switch for computing voice latents
2023-02-12 18:11:40 +00:00
2210b49cb6
fixed regression with computing conditional latencies outside of the CPU
2023-02-12 17:44:39 +00:00
a2d95fe208
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
25e70dce1a
instll python3.9, wrapped try/catch when parsing args.listen in case you somehow manage to insert garbage into that field and fuck up your config, removed a very redudnant setup.py install call since that only is required if you're just going to install it for using outside of the tortoise-tts folder
2023-02-12 04:35:21 +00:00
84316d8f80
Moved experimental settings to main tab, hidden under a check box
2023-02-11 17:21:08 +00:00
c5337a6b51
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
9bf1ea5b0a
History tab (3/10 it works)
2023-02-11 01:45:25 +00:00
7471bc209c
Moved voices out of the tortoise folder because it kept being processed for setup.py
2023-02-10 20:11:56 +00:00
2bce24b9dd
Cleanup
2023-02-10 19:55:33 +00:00
f5ed5499a0
Added a link to the colab notebook
2023-02-10 16:26:13 +00:00
39b81318f2
Added new options: "Output Sample Rate", "Output Volume", and documentation
2023-02-10 03:02:09 +00:00
3621e16ef9
Added 'Only Load Models Locally' setting
2023-02-09 22:06:55 +00:00
dccedc3f66
Added and documented
2023-02-09 21:07:51 +00:00
38ee19cd57
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
a37546ad99
owari da...
2023-02-09 01:53:25 +00:00
6255c98006
beginning to add DirectML support
2023-02-08 23:03:52 +00:00
d9a9fa6a82
Added two flags/settings: embed output settings, slimmer computed voice latents
2023-02-08 14:14:28 +00:00
6ebdde58f0
(finally) added the CVVP model weigh slider, latents export more data too for weighing against CVVP
2023-02-07 20:55:56 +00:00
6515d3b6de
added shell scripts for linux, wrapped sorted() for voice list, I guess
2023-02-06 21:54:31 -06:00
be6fab9dcb
added setting to adjust autoregressive sample batch size
2023-02-06 22:31:06 +00:00
100b4d7e61
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
5affc777e0
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
2cfd3bc213
updated README (before I go mad trying to nitpick and edit it while getting distracted from an iToddler sperging)
2023-02-06 00:56:17 +00:00
945136330c
Forgot to rename the cached latents to the new filename
2023-02-05 23:51:52 +00:00
5bf21fdbe1
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
1c582b5dc8
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
8831522de9
New tunable: pause size/breathing room (governs pause at the end of clips)
2023-02-05 14:45:51 +00:00
bc567d7263
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
d29ba75dd6
cleaned up element order with Blocks, also added preset updating the samples/iterations counts
2023-02-05 03:53:46 +00:00
5c876b81f3
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
43f45274dd
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
74f447e5d0
QoL fixes
2023-02-02 21:13:28 +00:00
James Betker
5dc3e269b3
Merge pull request #233 from kianmeng/fix-typos
...
Fix typos
2023-01-17 18:24:24 -07:00
chris
7ce3dc7bf1
add explicit requirements.txt usage for dep installation
2023-01-11 10:50:18 -05:00
원빈 정
b3d67dcc6b
Add reference of univnet implementation
2023-01-06 15:57:02 +09:00
Kian-Meng Ang
551fe655ff
Fix typos
...
Found via `codespell -S *.json -L splitted,nd,ser,broadcat`
2023-01-06 11:04:36 +08:00
James Betker
f28a116b48
Update README.md
2022-12-05 13:16:36 -08:00
Harry Coultas Blum
2efc5a3e50
Added keyword argument
2022-07-08 14:28:24 +01:00
James Betker
00f8bc5e78
Update README.md
2022-06-23 15:57:50 -07:00
Jai Mu
5bff5dd819
Update README.md
...
Useless update but it was bothering me.
2022-05-22 00:56:06 +09:30
James Betker
5d5aacc38c
v2.4
2022-05-17 12:15:13 -06:00
James Betker
8c0b3855bf
Release notes for 2.3
2022-05-12 20:26:24 -06:00
James Betker
099bf8363c
Update README with suggestions for windows installation
2022-05-08 20:44:44 -06:00
James Betker
ffd0238a16
v2.2
2022-05-06 00:11:10 -06:00
James Betker
b327be56c6
Update readme with prompt engineering
2022-05-03 21:32:06 -06:00
James Betker
e93e5a0c16
Add setup
2022-05-02 21:24:34 -06:00
James Betker
98afa484f1
Update README and update to version 2.1
2022-05-02 21:02:29 -06:00
James Betker
a4cda68ddf
getting ready for 2.1 release
2022-05-02 20:20:50 -06:00
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
