2830d1fa96
fixed setup scripts and Dockerfile to NOT use extra-index-url and instead use index-url (how this happened I don't know, since pytorch instructions use index-url), '''fixed''' phonemizing japanese for VALL-E with pykakasi
2023-10-12 00:27:46 +00:00
17acfee5d0
fixed culling for validation based on audio duration not working
2023-09-21 22:33:11 +00:00
5f80ee9b38
set use-deepspeed to false because it's not a dependency and installing it as a dependency under windows is a huge nightmare
2023-09-04 22:09:09 +00:00
ken11o2
29c270d1cc
master ( #369 )
...
Add DeepSpeed feature for tortoise
Reviewed-on: mrq/ai-voice-cloning#369
Co-authored-by: ken11o2 <ken11o2@noreply.localhost>
Co-committed-by: ken11o2 <ken11o2@noreply.localhost>
2023-09-04 22:04:00 +00:00
7fc8f4c45a
slight fixes
2023-09-03 12:34:55 +00:00
mrq
7110b878b7
Merge pull request 'Websocket fixes / additions' ( #350 ) from ben_mkiv/ai-voice-cloning:master into master
...
Reviewed-on: mrq/ai-voice-cloning#350
2023-08-30 18:39:32 +00:00
13b65d8775
Merge branch 'master' of https://git.ecker.tech/ben_mkiv/ai-voice-cloning
2023-08-26 17:43:35 +02:00
b72f2216bf
added websocket server arguments to enabled it (now disabled by default) and to specify the address/port to listen on
2023-08-26 17:38:58 +02:00
690947ad36
Do not double phonemize if using VALL-E backend (I wonder how many hours I've wasted from this oversight)
2023-08-26 00:02:17 +00:00
6f0f148782
websocket server: fix for model loading (just overriding args didn't do it after all...)
2023-08-26 01:41:29 +02:00
578a5bcadd
websocket server: fix for model loading (just overriding args didn't do it after all...)
2023-08-26 01:40:35 +02:00
b4dc103931
I don't know how I did not commit the 'sample from the voices to construct the input prompt for vall-e' change but this helps
2023-08-25 04:26:48 +00:00
a657623cbc
updated vall-e training template to use path-based speakers because it would just have a batch/epoch size of 1 otherwise; revert hardcoded 'spit processed dataset to this path' from my training rig to spit it out in a sane spot
2023-08-24 21:45:50 +00:00
533b73e083
fixed the overwrite regression for bark and vall-e backends too
2023-08-24 19:46:42 +00:00
f5fab33e9c
fixed defaults for vall-e backend
2023-08-24 19:44:52 +00:00
mrq
4aa240d48a
Merge pull request 'fix filename generation which didn't work and overwrote existing files' ( #341 ) from ben_mkiv/ai-voice-cloning:master into master
...
Reviewed-on: mrq/ai-voice-cloning#341
2023-08-24 12:29:59 +00:00
00b173857d
fix filename generation which didn't work and overwrote existing files
2023-08-24 09:57:01 +02:00
dc46fdc7d0
fixed another issue from haphazardly copying my changes from my training machine
2023-08-23 22:09:22 +00:00
29290f574e
should fix issue that arises when trying to prepare the dataset without slicing segments
2023-08-23 21:49:22 +00:00
ce24ba41e2
Websocket server, override args parameters for model settings (squashed)
...
Revert "favor existing arguments from parameters (kwargs) over global (args)"
This reverts commit 89102347a956ebcfe9a83ae7d1aa1336f1c53483.
args are now updated in the websocket server
2023-08-23 19:40:39 +02:00
5d73d9e71c
small QoL change to the StringNone helper, to allow generated text to be "None", maybe someone wants to generate that, we never know...
2023-08-22 21:49:49 +02:00
9abcb0f193
websocket server: API change(!), better response format
2023-08-22 21:37:19 +02:00
1ec3344999
Merge branch 'master' of https://git.ecker.tech/ben_mkiv/ai-voice-cloning
2023-08-22 21:00:06 +02:00
a902913780
websocket server: workaround for values and None type
2023-08-22 20:20:49 +02:00
2060b6f21c
fixed issue with sliced audio being the wrong sample rate
2023-08-22 14:22:39 +00:00
eeddd4cb6b
forgot the important reason I even started working on AIVC again
2023-08-21 03:42:12 +00:00
72a38ff2fc
made initialization faster if there's a lot of voice files (because glob fucking sucks), commiting changes buried on my training rig
2023-08-21 03:31:49 +00:00
2626364c40
added simple websocket server which allows to start tts generation tasks, retrieving autoregressive models and voices list
2023-08-16 12:51:13 +02:00
ac645e0a20
no longer need to install bark under ./modules/
2023-07-11 16:20:28 +00:00
e2a6dc1c0a
under bark, properly use transcribed audio if the audio wasn't actually sliced (oops)
2023-07-11 14:53:32 +00:00
6c3f48efba
uses gitmylo/bark-voice-cloning-HuBERT-quantizer for creating custom voices (it slightly works better over the base method, but still not very good desu)
2023-07-03 02:46:10 +00:00
547e1d1277
updated bark support, it'll also query for vocos, it actually works (I don't know what specifically was the issue)
2023-07-03 01:22:02 +00:00
76ed34ddd2
added CLI script (python ./src/cli.py --text=TEXT --voice=VOICE' etc)
2023-06-11 04:46:22 +00:00
e227ab8e08
updated whisperX integration for use with the latest version (v3) (NOTE: you WILL need to also update whisperx if you pull this commit)
2023-06-09 02:41:29 +00:00
805d7d35e8
the power of a separate setup for testing
2023-05-22 17:36:28 +00:00
2f5486a8d5
oops
2023-05-21 23:24:13 +00:00
baa6b76b85
added gradio API for changing AR model
2023-05-21 23:20:39 +00:00
31da215c5f
added checkboxes to use the original method for calculating latents (ignores the voice chunk field)
2023-05-21 01:47:48 +00:00
cbe21745df
I am very smart (need to validate)
2023-05-12 17:41:26 +00:00
74bd0f0cdc
revert local change that made its way upstream (showing graphs by it instead of epoch)
2023-05-11 03:30:54 +00:00
149aaca554
fixed the whisperx has no attribute named load_model whatever because I guess whisperx has as stable of an API as I do
2023-05-06 10:45:17 +00:00
e416b0fe6f
oops
2023-05-05 12:36:48 +00:00
5003bc89d3
cleaned up brain worms with wrapping around gradio progress by instead just using tqdm directly (slight regressions with some messages not getting pushed)
2023-05-04 23:40:33 +00:00
09d849a78f
quick hotfix if it actually is a problem in the repo itself
2023-05-04 23:01:47 +00:00
853c7fdccf
forgot to uncomment the block to transcribe and slice when using transcribe all because I was piece-processing a huge batch of LibriTTS and somehow that leaked over to the repo
2023-05-03 21:31:37 +00:00
eddb8aaa9a
indentation fix
2023-04-28 15:56:57 +00:00
99387920e1
backported caching of phonemizer backend from mrq/vall-e
2023-04-28 15:31:45 +00:00
c5e9b407fa
boolean oops
2023-04-27 14:40:22 +00:00
3978921e71
forgot to make the transcription tab visible with the bark backend (god the code is a mess now, I'll suck you off if you clean this up for me (not really))
2023-04-26 04:55:10 +00:00
b6440091fb
Very, very, VERY, barebones integration with Bark (documentation soon)
2023-04-26 04:48:09 +00:00
