a-One-Fan
/
ai-voice-cloning-oneapi
forked from mrq/ai-voice-cloning
1
0
Fork 0
Code Pull Requests Activity
335 Commits
1 Branch
0 Tags
470 KiB
Commit Graph

335 Commits (master)
 

Author SHA1 Message Date
a-One-Fan ae7916a22f Do inplace sed 2023-07-13 10:24:31 +07:00
a-One-Fan 9f5b4cfeb6 More convenient setup for this fork 2023-07-13 10:10:01 +07:00
a-One-Fan 26a3ad9378 Update requirements to match master 2023-07-13 10:05:39 +07:00
a-One-Fan 27024a7b38 Add oneAPI training support (ai-voice-cloning) 
- Add an argument to use oneAPI when training
- Use it in the oneAPI startup
- Set an env var when doing so
- Initialize distributed training with ccl when doing so
Intel does not and will not support non-distributed training. I think that's a good decision.
The message that training will happen with oneAPI gets printed twice.
 2023-05-04 20:51:31 +07:00
a-One-Fan 5092cf9174 Use ipexrun / better start 
Supposedly, ipexrun improves performance by ~10%. It needs numactl.
Also deactivate any conda envs since working with oneAPI might mean having a conda env open.
This just reduces spam from setvars.sh.
 2023-05-04 20:46:02 +07:00
a-One-Fan c62d73f28a Chmod start-oneapi.sh so it can actually be ran 2023-05-04 16:12:26 +07:00
a-One-Fan 7fedff0b1f Make oneAPI startup its own file 
Not sed-ing seems like a better idea, in case the user wants to revert it easily or something, or for updates.
 2023-05-02 00:20:34 +07:00
a-One-Fan 7261ec2b1f Use all custom wheels. 
Intel's stable wheels that were released a day or so prior have a VRAM leak, or some other VRAM usage issue in general.
Also adds CCL, the stable wheels for which seem fine (?)
 2023-05-01 23:19:10 +07:00
a-One-Fan bd5e0c1d56 Add initial setup file 2023-04-30 19:13:25 +07:00
mrq fd306d850d updated setup-directml.bat to not hard require torch version because it's updated to torch2 now 2023-04-29 00:50:16 +07:00
mrq eddb8aaa9a indentation fix 2023-04-28 15:56:57 +07:00
mrq 99387920e1 backported caching of phonemizer backend from mrq/vall-e 2023-04-28 15:31:45 +07:00
mrq c5e9b407fa boolean oops 2023-04-27 14:40:22 +07:00
mrq 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 +07:00
mrq b6440091fb Very, very, VERY, barebones integration with Bark (documentation soon) 2023-04-26 04:48:09 +07:00
mrq faa8da12d7 modified logic to determine valid voice folders, also allows subdirs within the folder (for example: ./voices/SH/james/ will be named SH/james) 2023-04-13 21:10:38 +07:00
mrq 02beb1dd8e should fix #203 2023-04-13 03:14:06 +07:00
mrq 8f3e9447ba disable diarize button 2023-04-12 20:03:54 +07:00
mrq d8b996911c a bunch of shit i had uncommited over the past while pertaining to VALL-E 2023-04-12 20:02:46 +07:00
mrq b785192dfc Merge pull request 'Make convenient to use with Docker' (#191) from psr/ai-voice-cloning:docker into master 
Reviewed-on: mrq/ai-voice-cloning#191
 2023-04-08 14:04:45 +07:00
psr 9afafc69c1 docker: add training script 2023-04-07 23:15:13 +07:00
psr c018bfca9c docker: add ffmpeg for whisper and general cleanup 2023-04-07 23:14:05 +07:00
psr d64cba667f docker support 2023-04-07 21:52:18 +07:00
mrq 0440eac2bc #185 2023-03-31 06:55:52 +07:00
mrq 9f64153a28 fixes #185 2023-03-31 06:03:56 +07:00
mrq 4744120be2 added VALL-E inference support (very rudimentary, gimped, but it will load a model trained on a config generated through the web UI) 2023-03-31 03:26:00 +07:00
mrq 9b01377667 only include auto in the list of models under setting, nothing else 2023-03-29 19:53:23 +07:00
mrq f66281f10c added mixing models (shamelessly inspired from voldy's web ui) 2023-03-29 19:29:13 +07:00
mrq c89c648b4a fixes #176 2023-03-26 11:05:50 +07:00
mrq 41d47c7c2a for real this time show those new vall-e metrics 2023-03-26 04:31:50 +07:00
mrq c4ca04cc92 added showing reported training accuracy and eval/validation metrics to graph 2023-03-26 04:08:45 +07:00
mrq 8c647c889d now there should be feature parity between trainers 2023-03-25 04:12:03 +07:00
mrq fd9b2e082c x_lim and y_lim for graph 2023-03-25 02:34:14 +07:00
mrq 9856db5900 actually make parsing VALL-E metrics work 2023-03-23 15:42:51 +07:00
mrq 69d84bb9e0 I forget 2023-03-23 04:53:31 +07:00
mrq 444bcdaf62 my sanitizer actually did work, it was just batch sizes leading to problems when transcribing 2023-03-23 04:41:56 +07:00
mrq a6daf289bc when the sanitizer thingy works in testing but it doesn't outside of testing, and you have to retranscribe for the fourth time today 2023-03-23 02:37:44 +07:00
mrq 86589fff91 why does this keep happening to me 2023-03-23 01:55:16 +07:00
mrq 0ea93a7f40 more cleanup, use 24KHz for preparing for VALL-E (encodec will resample to 24Khz anyways, makes audio a little nicer), some other things 2023-03-23 01:52:26 +07:00
mrq d2a9ab9e41 remove redundant phonemize for vall-e (oops), quantize all files and then phonemize all files for cope optimization, load alignment model once instead of for every transcription (speedup with whisperx) 2023-03-23 00:22:25 +07:00
mrq 19c0854e6a do not write current whisper.json if there's no changes 2023-03-22 22:24:07 +07:00
mrq 932eaccdf5 added whisper transcription 'sanitizing' (collapse very short transcriptions to the previous segment) (I really have to stop having several copies spanning several machines for AIVC, I keep reverting shit) 2023-03-22 22:10:01 +07:00
mrq 736cdc8926 disable diarization for whisperx as it's just a useless performance hit (I don't have anything that's multispeaker within the same audio file at the moment) 2023-03-22 20:38:58 +07:00
mrq aa5bdafb06 ugh 2023-03-22 20:26:28 +07:00
mrq 13605f980c now whisperx should output json that aligns with what's expected 2023-03-22 20:01:30 +07:00
mrq 8877960062 fixes for whisperx batching 2023-03-22 19:53:42 +07:00
mrq 4056a27bcb begrudgingly added back whisperx integration (VAD/Diarization testing, I really, really need accurate timestamps before dumping mondo amounts of time on training a dataset) 2023-03-22 19:24:53 +07:00
mrq b8c3c4cfe2 Fixed #167 2023-03-22 18:21:37 +07:00
mrq da96161aaa oops 2023-03-22 18:07:46 +07:00
mrq f822c87344 cleanups, realigning vall-e training 2023-03-22 17:47:23 +07:00