Commit Graph

383 Commits

Author SHA1 Message Date
71b676060a allow using 0.01 in save frequncy for large datasets 2024-02-15 13:01:07 +00:00
mrq
94f88886b0 updated colab notebook 2023-10-24 23:39:46 +00:00
mrq
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
mrq
17acfee5d0 fixed culling for validation based on audio duration not working 2023-09-21 22:33:11 +00:00
mrq
2fae5008fc Merge pull request 'Freeze beartype==0.15.0' (#393) from Jarod/ai-voice-cloning:master into master
Reviewed-on: mrq/ai-voice-cloning#393
2023-09-19 02:25:04 +00:00
7dd8b740e8 freeze beartype==0.15.0, unfrozen comes from x-clip in dlas 2023-09-18 17:18:44 -07:00
mrq
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
mrq
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
mrq
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
mrq
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
mrq
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
mrq
533b73e083 fixed the overwrite regression for bark and vall-e backends too 2023-08-24 19:46:42 +00:00
mrq
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
mrq
dc46fdc7d0 fixed another issue from haphazardly copying my changes from my training machine 2023-08-23 22:09:22 +00:00
mrq
29290f574e should fix issue that arises when trying to prepare the dataset without slicing segments 2023-08-23 21:49:22 +00:00
mrq
0a5483e57a updated valle yaml template 2023-08-23 21:42:32 +00:00
mrq
e613299304 Merge pull request 'favor existing arguments from parameters (kwargs) over global (args)' (#336) from ben_mkiv/ai-voice-cloning:master into master
Reviewed-on: mrq/ai-voice-cloning#336
2023-08-23 21:05:36 +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
mrq
5f4215b3ef Merge pull request 'websocket server: API change(!), better response format' (#334) from ben_mkiv/ai-voice-cloning:master into master
Reviewed-on: mrq/ai-voice-cloning#334
2023-08-22 20:35:42 +00:00
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
mrq
fb1cfd059f Merge pull request 'websocket server: small fix' (#333) from ben_mkiv/ai-voice-cloning:master into master
Reviewed-on: mrq/ai-voice-cloning#333
2023-08-22 19:26:37 +00:00
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
mrq
2060b6f21c fixed issue with sliced audio being the wrong sample rate 2023-08-22 14:22:39 +00:00
mrq
eeddd4cb6b forgot the important reason I even started working on AIVC again 2023-08-21 03:42:12 +00:00
mrq
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
mrq
91a0c495ff Merge pull request 'added simple websocket server which allows to start tts generation tasks, retrieving autoregressive models and voices list' (#328) from ben_mkiv/ai-voice-cloning:master into master
Reviewed-on: mrq/ai-voice-cloning#328
2023-08-16 14:01:44 +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
mrq
ac645e0a20 no longer need to install bark under ./modules/ 2023-07-11 16:20:28 +00:00
mrq
e2a6dc1c0a under bark, properly use transcribed audio if the audio wasn't actually sliced (oops) 2023-07-11 14:53:32 +00:00
mrq
a325496661 Merge pull request 'Freeze pydantic package to 1.10.11' (#301) from Jarod/ai-voice-cloning:master into master
Reviewed-on: mrq/ai-voice-cloning#301
2023-07-09 15:06:31 +00:00
Jarod
350d2d5a95 Freeze pydantic package to 1.10.11
inflect in DLAS requirements.txt installs pydantic 2.0.2, causing issues with the Gradio Webpage
2023-07-09 02:36:23 +00:00
mrq
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
mrq
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
mrq
76ed34ddd2 added CLI script (python ./src/cli.py --text=TEXT --voice=VOICE' etc) 2023-06-11 04:46:22 +00:00
mrq
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
mrq
805d7d35e8 the power of a separate setup for testing 2023-05-22 17:36:28 +00:00
mrq
2f5486a8d5 oops 2023-05-21 23:24:13 +00:00
mrq
baa6b76b85 added gradio API for changing AR model 2023-05-21 23:20:39 +00:00
mrq
31da215c5f added checkboxes to use the original method for calculating latents (ignores the voice chunk field) 2023-05-21 01:47:48 +00:00
mrq
9e3eca2261 freeze gradio because I forgot to do it last week when it broke 2023-05-18 14:45:49 +00:00