Commit Graph

  • cce3e098c7 RIP 1734867194603465784/tmp_refs/heads/master 1734867194603465784/master 1734866833835031879/tmp_refs/heads/master 1734866833835031879/master 1723415243722149972/tmp_refs/heads/master 1723415243722149972/master 1719218420832309694/tmp_refs/heads/master 1719218420832309694/master 1716601886326372183/tmp_refs/heads/master 1716601886326372183/master mrq 2024-04-27 20:11:14 -0500
  • 94f88886b0 updated colab notebook 1710075533676620909/tmp_refs/heads/master 1710075533676620909/master mrq 2023-10-24 23:39:46 +0000
  • 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 mrq 2023-10-12 00:27:46 +0000
  • 17acfee5d0 fixed culling for validation based on audio duration not working mrq 2023-09-21 22:33:11 +0000
  • 2fae5008fc Merge pull request 'Freeze beartype==0.15.0' (#393) from Jarod/ai-voice-cloning:master into master mrq 2023-09-19 02:25:04 +0000
  • 7dd8b740e8 freeze beartype==0.15.0, unfrozen comes from x-clip in dlas Jarod Mica 2023-09-18 17:18:44 -0700
  • 5f80ee9b38 set use-deepspeed to false because it's not a dependency and installing it as a dependency under windows is a huge nightmare mrq 2023-09-04 22:09:09 +0000
  • 29c270d1cc master (#369) ken11o2 2023-09-04 22:04:00 +0000
  • 7fc8f4c45a slight fixes mrq 2023-09-03 12:34:55 +0000
  • 7110b878b7 Merge pull request 'Websocket fixes / additions' (#350) from ben_mkiv/ai-voice-cloning:master into master mrq 2023-08-30 18:39:32 +0000
  • 13b65d8775 Merge branch 'master' of https://git.ecker.tech/ben_mkiv/ai-voice-cloning ben_mkiv 2023-08-26 17:43:35 +0200
  • b72f2216bf added websocket server arguments to enabled it (now disabled by default) and to specify the address/port to listen on ben_mkiv 2023-08-26 17:38:58 +0200
  • 690947ad36 Do not double phonemize if using VALL-E backend (I wonder how many hours I've wasted from this oversight) mrq 2023-08-26 00:02:17 +0000
  • 6f0f148782 websocket server: fix for model loading (just overriding args didn't do it after all...) ben_mkiv 2023-08-26 01:40:35 +0200
  • 578a5bcadd websocket server: fix for model loading (just overriding args didn't do it after all...) ben_mkiv 2023-08-26 01:40:35 +0200
  • 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 mrq 2023-08-25 04:26:48 +0000
  • 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 mrq 2023-08-24 21:45:50 +0000
  • 533b73e083 fixed the overwrite regression for bark and vall-e backends too mrq 2023-08-24 19:46:42 +0000
  • f5fab33e9c fixed defaults for vall-e backend mrq 2023-08-24 19:44:52 +0000
  • 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 mrq 2023-08-24 12:29:59 +0000
  • 00b173857d fix filename generation which didn't work and overwrote existing files ben_mkiv 2023-08-24 09:57:01 +0200
  • dc46fdc7d0 fixed another issue from haphazardly copying my changes from my training machine mrq 2023-08-23 22:09:22 +0000
  • 29290f574e should fix issue that arises when trying to prepare the dataset without slicing segments mrq 2023-08-23 21:49:22 +0000
  • 0a5483e57a updated valle yaml template mrq 2023-08-23 21:42:32 +0000
  • e613299304 Merge pull request 'favor existing arguments from parameters (kwargs) over global (args)' (#336) from ben_mkiv/ai-voice-cloning:master into master mrq 2023-08-23 21:05:36 +0000
  • ce24ba41e2 Websocket server, override args parameters for model settings (squashed) ben_mkiv 2023-08-22 23:09:42 +0200
  • 5f4215b3ef Merge pull request 'websocket server: API change(!), better response format' (#334) from ben_mkiv/ai-voice-cloning:master into master mrq 2023-08-22 20:35:42 +0000
  • 5d73d9e71c small QoL change to the StringNone helper, to allow generated text to be "None", maybe someone wants to generate that, we never know... ben_mkiv 2023-08-22 21:49:49 +0200
  • 9abcb0f193 websocket server: API change(!), better response format ben_mkiv 2023-08-22 21:37:19 +0200
  • fb1cfd059f Merge pull request 'websocket server: small fix' (#333) from ben_mkiv/ai-voice-cloning:master into master mrq 2023-08-22 19:26:37 +0000
  • 1ec3344999 Merge branch 'master' of https://git.ecker.tech/ben_mkiv/ai-voice-cloning ben_mkiv 2023-08-22 21:00:06 +0200
  • a902913780 websocket server: workaround for values and None type ben_mkiv 2023-08-22 20:20:49 +0200
  • 2060b6f21c fixed issue with sliced audio being the wrong sample rate mrq 2023-08-22 14:22:39 +0000
  • eeddd4cb6b forgot the important reason I even started working on AIVC again mrq 2023-08-21 03:42:12 +0000
  • 72a38ff2fc made initialization faster if there's a lot of voice files (because glob fucking sucks), commiting changes buried on my training rig mrq 2023-08-21 03:31:49 +0000
  • 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 mrq 2023-08-16 14:01:44 +0000
  • 2626364c40 added simple websocket server which allows to start tts generation tasks, retrieving autoregressive models and voices list ben_mkiv 2023-08-16 12:51:13 +0200
  • ac645e0a20 no longer need to install bark under ./modules/ mrq 2023-07-11 16:20:28 +0000
  • e2a6dc1c0a under bark, properly use transcribed audio if the audio wasn't actually sliced (oops) mrq 2023-07-11 14:53:32 +0000
  • a325496661 Merge pull request 'Freeze pydantic package to 1.10.11' (#301) from Jarod/ai-voice-cloning:master into master mrq 2023-07-09 15:06:31 +0000
  • 350d2d5a95 Freeze pydantic package to 1.10.11 Jarod 2023-07-09 02:36:23 +0000
  • 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) mrq 2023-07-03 02:46:10 +0000
  • 547e1d1277 updated bark support, it'll also query for vocos, it actually works (I don't know what specifically was the issue) mrq 2023-07-03 01:22:02 +0000
  • 76ed34ddd2 added CLI script (python ./src/cli.py --text=TEXT --voice=VOICE' etc) mrq 2023-06-11 04:46:22 +0000
  • e227ab8e08 updated whisperX integration for use with the latest version (v3) (NOTE: you WILL need to also update whisperx if you pull this commit) mrq 2023-06-09 02:41:29 +0000
  • 805d7d35e8 the power of a separate setup for testing mrq 2023-05-22 17:36:28 +0000
  • 2f5486a8d5 oops mrq 2023-05-21 23:24:13 +0000
  • baa6b76b85 added gradio API for changing AR model mrq 2023-05-21 23:20:39 +0000
  • 31da215c5f added checkboxes to use the original method for calculating latents (ignores the voice chunk field) mrq 2023-05-21 01:47:48 +0000
  • 9e3eca2261 freeze gradio because I forgot to do it last week when it broke mrq 2023-05-18 14:45:49 +0000
  • cbe21745df I am very smart (need to validate) mrq 2023-05-12 17:41:26 +0000
  • 74bd0f0cdc revert local change that made its way upstream (showing graphs by it instead of epoch) mrq 2023-05-11 03:30:54 +0000
  • 149aaca554 fixed the whisperx has no attribute named load_model whatever because I guess whisperx has as stable of an API as I do mrq 2023-05-06 10:45:17 +0000
  • e416b0fe6f oops mrq 2023-05-05 12:36:48 +0000
  • 5003bc89d3 cleaned up brain worms with wrapping around gradio progress by instead just using tqdm directly (slight regressions with some messages not getting pushed) mrq 2023-05-04 23:40:33 +0000
  • 09d849a78f quick hotfix if it actually is a problem in the repo itself mrq 2023-05-04 23:01:47 +0000
  • 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 mrq 2023-05-03 21:31:37 +0000
  • fd306d850d updated setup-directml.bat to not hard require torch version because it's updated to torch2 now mrq 2023-04-29 00:50:16 +0000
  • eddb8aaa9a indentation fix mrq 2023-04-28 15:56:57 +0000
  • 99387920e1 backported caching of phonemizer backend from mrq/vall-e mrq 2023-04-28 15:31:45 +0000
  • c5e9b407fa boolean oops mrq 2023-04-27 14:40:22 +0000
  • 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)) mrq 2023-04-26 04:55:10 +0000
  • b6440091fb Very, very, VERY, barebones integration with Bark (documentation soon) mrq 2023-04-26 04:48:09 +0000
  • faa8da12d7 modified logic to determine valid voice folders, also allows subdirs within the folder (for example: ./voices/SH/james/ will be named SH/james) mrq 2023-04-13 21:10:38 +0000
  • 02beb1dd8e should fix #203 mrq 2023-04-13 03:14:06 +0000
  • 8f3e9447ba disable diarize button mrq 2023-04-12 20:03:54 +0000
  • d8b996911c a bunch of shit i had uncommited over the past while pertaining to VALL-E mrq 2023-04-12 20:02:46 +0000
  • b785192dfc Merge pull request 'Make convenient to use with Docker' (#191) from psr/ai-voice-cloning:docker into master mrq 2023-04-08 14:04:45 +0000
  • 9afafc69c1 docker: add training script psr 2023-04-07 23:15:13 +0000
  • c018bfca9c docker: add ffmpeg for whisper and general cleanup psr 2023-04-07 23:14:05 +0000
  • d64cba667f docker support psr 2023-04-05 22:38:53 +0000
  • 0440eac2bc #185 mrq 2023-03-31 06:55:52 +0000
  • 9f64153a28 fixes #185 mrq 2023-03-31 06:03:56 +0000
  • 4744120be2 added VALL-E inference support (very rudimentary, gimped, but it will load a model trained on a config generated through the web UI) mrq 2023-03-31 03:26:00 +0000
  • 9b01377667 only include auto in the list of models under setting, nothing else mrq 2023-03-29 19:53:23 +0000
  • f66281f10c added mixing models (shamelessly inspired from voldy's web ui) mrq 2023-03-29 19:29:13 +0000
  • c89c648b4a fixes #176 mrq 2023-03-26 11:05:50 +0000
  • 41d47c7c2a for real this time show those new vall-e metrics mrq 2023-03-26 04:31:50 +0000
  • c4ca04cc92 added showing reported training accuracy and eval/validation metrics to graph mrq 2023-03-26 04:08:45 +0000
  • 8c647c889d now there should be feature parity between trainers mrq 2023-03-25 04:12:03 +0000
  • fd9b2e082c x_lim and y_lim for graph mrq 2023-03-25 02:34:14 +0000
  • 9856db5900 actually make parsing VALL-E metrics work mrq 2023-03-23 15:42:51 +0000
  • 69d84bb9e0 I forget mrq 2023-03-23 04:53:31 +0000
  • 444bcdaf62 my sanitizer actually did work, it was just batch sizes leading to problems when transcribing mrq 2023-03-23 04:41:56 +0000
  • 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 mrq 2023-03-23 02:37:44 +0000
  • 86589fff91 why does this keep happening to me mrq 2023-03-23 01:55:16 +0000
  • 0ea93a7f40 more cleanup, use 24KHz for preparing for VALL-E (encodec will resample to 24Khz anyways, makes audio a little nicer), some other things mrq 2023-03-23 01:52:26 +0000
  • 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) mrq 2023-03-23 00:22:25 +0000
  • 19c0854e6a do not write current whisper.json if there's no changes mrq 2023-03-22 22:24:07 +0000
  • 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) mrq 2023-03-22 22:10:01 +0000
  • 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) mrq 2023-03-22 20:38:58 +0000
  • aa5bdafb06 ugh mrq 2023-03-22 20:26:28 +0000
  • 13605f980c now whisperx should output json that aligns with what's expected mrq 2023-03-22 20:01:30 +0000
  • 8877960062 fixes for whisperx batching mrq 2023-03-22 19:53:42 +0000
  • 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) mrq 2023-03-22 19:24:53 +0000
  • b8c3c4cfe2 Fixed #167 mrq 2023-03-22 18:21:37 +0000
  • da96161aaa oops mrq 2023-03-22 18:07:46 +0000
  • f822c87344 cleanups, realigning vall-e training mrq 2023-03-22 17:47:23 +0000
  • 909325bb5a ugh mrq 2023-03-21 22:18:57 +0000
  • 5a5fd9ca87 Added option to unsqueeze sample batches after sampling mrq 2023-03-21 21:34:26 +0000