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
James Betker
23a3d5d00b
Move everything into the tortoise/ subdirectory
...
For eventual packaging.
2022-05-01 16:24:24 -06:00
James Betker
9c35b73a1f
navy seal copypasta
...
(for the memes)
2022-05-01 14:55:06 -06:00
James Betker
d0caf7e695
add option to specify model directory to API
2022-05-01 14:51:44 -06:00
James Betker
354b4ea0ea
update citation file
2022-04-28 23:11:09 -06:00
James Betker
31a4be3b9f
add citation file
2022-04-28 23:09:33 -06:00
James Betker
782a55d0cd
allow mp3 voices
2022-04-28 17:38:37 -06:00
James Betker
e8966d09cf
ack
2022-04-27 23:22:55 -06:00
James Betker
9d761673d8
add librosa to reqs
2022-04-27 09:33:43 -06:00
James Betker
e969243c79
add scipy to requirements
2022-04-27 09:25:00 -06:00
James Betker
3dc66ba308
Revert "Merge pull request #3 from osanseviero/main"
...
This reverts commit 1a41f7f769cf7a4bc7e7
2022-04-27 09:15:55 -06:00
James Betker
090c650b85
Revert "fix site and ipynb with new paths"
...
This reverts commit 7d54ef8cc5
2022-04-27 09:15:39 -06:00
James Betker
d80371b5e6
fix site and ipynb with new paths
2022-04-27 09:07:35 -06:00
James Betker
04dcc01615
Merge pull request #3 from osanseviero/main
...
Misc improvements and packaging
2022-04-27 09:01:32 -06:00
osanseviero
77a25ebdd2
Package everything
2022-04-27 15:04:15 +02:00
James Betker
d37f44ba28
add reference clips to examples
2022-04-26 10:45:02 -06:00
James Betker
5bd6f0fb9c
tortoise-detect docs
2022-04-26 10:37:44 -06:00
James Betker
28c5906907
ok
2022-04-26 10:27:57 -06:00
James Betker
1d79b44aef
is this from tortoise?
2022-04-26 10:24:34 -06:00
James Betker
1f8eef2807
classifier proto
2022-04-26 09:54:08 -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
f3e17662cc
fix notebook
2022-04-25 21:17:49 -06:00
James Betker
8606680545
gi
2022-04-25 20:45:09 -06:00
James Betker
c30e67cae3
check in some sample results
2022-04-25 20:44:58 -06:00
James Betker
55c732f38e
move voices
2022-04-25 20:07:07 -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
b2ffe02c2d
n/c
2022-04-22 11:34:05 -06:00
James Betker
3735a819b3
update requirements and some docs
2022-04-21 16:06:43 -06:00
James Betker
9f28b005f3
update read to output concatenated audio
2022-04-21 15:19:36 -06:00
James Betker
5d9a1a058f
:(
2022-04-20 18:06:29 -06:00
James Betker
2347d16333
remove xt dep
2022-04-20 18:00:12 -06:00
James Betker
ca31a1c9f7
update clvp path
2022-04-20 17:59:34 -06:00
James Betker
eef09d4e8f
updates to scripts
2022-04-20 17:24:09 -06:00
James Betker
d7f81617b3
y u no cvvp
2022-04-18 20:47:16 -06:00
James Betker
89bb33c839
AND OTHER DEPS
2022-04-18 20:44:22 -06:00
James Betker
412a441c86
remove dependency on x-transformers
2022-04-18 20:43:04 -06:00
James Betker
078274f055
update to v2 models (clvp pending)
2022-04-18 17:32:54 -06:00
James Betker
f717d24b0b
Support CVVP & fix for major bug in API
2022-04-18 14:47:44 -06:00
James Betker
a4bc51cb6d
yeah
2022-04-18 10:30:22 -06:00
James Betker
3f968bedb5
update do_tts
2022-04-18 10:22:36 -06:00
James Betker
4281b64517
Update autoregressive to support type inputs
2022-04-18 10:22:05 -06:00
James Betker
2dea4952d5
update api constants
2022-04-18 09:22:15 -06:00
James Betker
904561d250
update
2022-04-15 08:26:11 -06:00
James Betker
4aab81b074
implement clip-guided generation (and never use it...)
2022-04-14 21:50:57 -06:00
James Betker
cf80d7317c
Remove intelligibility refinement
...
It's not longer a concern. :)
2022-04-13 17:04:19 -06:00
James Betker
2eb5d4b0cb
Update sweep & eval_multiple with new voices
2022-04-13 17:03:36 -06:00
