aa96edde2fUpdated notebook to put userdata under a dedicated folder (and some safeties to not nuke them if you double run the script like I did thinking rm -r [symlink] would just remove the symlinkmrq2023-02-22 15:45:41 +0000
526a430c2ahow did this revert...mrq2023-02-22 13:24:03 +0000
2aa70532e8added '''suggested''' voice chunk size (it just updates it to how many files you have, not based on combined voice length, like it shouldmrq2023-02-22 03:31:46 +0000
9e64dad785clamp batch size to sample count when generating for the sickos that want that, added setting to remove non-final output after a generation, something else I forgot alreadymrq2023-02-21 21:50:05 +0000
f119993fb5explicitly use python3 because some OSs will not have python alias to python3, allow batch size 1mrq2023-02-21 20:20:52 +0000
8a1a48f31eAdded very experimental float16 training for cards with not enough VRAM (10GiB and below, maybe) \!NOTE\! this is VERY EXPERIMETNAL, I have zero free time to validate it right now, I'll do it latermrq2023-02-21 19:31:57 +0000
ed2cf9f5eewrap checking for metadata when adding a voice in case it throws an errormrq2023-02-21 17:35:30 +0000
bbc2d26289I finally figured out how to fix gr.Dropdown.change, so a lot of dumb UI decisions are fixed and makes sensemrq2023-02-21 03:00:45 +0000
7d1936adadactually cleaned the notebookmrq2023-02-20 23:12:53 +0000
1fd88afccaupdated notebook for newer setup structure, added formatting of getting it/s and lass loss rate (have not tested loss rate yet)mrq2023-02-20 22:56:39 +0000
bacac6daeahandled paths that contain spaces because python for whatever god forsaken reason will always split on spaces even if wrapping an argument in quotesmrq2023-02-20 20:23:22 +0000
37ffa60d14brain worms forgot a global, hate global semanticsmrq2023-02-20 15:31:38 +0000
d17f6fafb0clean up, reordered, added some rather liberal loading/unloading auxiliary models, can't really focus right now to keep testing it, report any issues and I'll get around to itmrq2023-02-20 00:21:16 +0000
ee95616dfdoptimize batch sizes to be as evenly divisible as possible (noticed the calculated epochs mismatched the inputted epochs)mrq2023-02-19 21:06:14 +0000
6260594a1eForgot to base print/save frequencies in terms of epochs in the UI, will get converted when saving the YAMLmrq2023-02-19 20:38:00 +0000
4694d622f4doing something completely unrelated had me realize it's 1000x easier to just base things in terms of epochs, and calculate iteratsions from theremrq2023-02-19 20:22:03 +0000
ec76676b16i hate gradio I hate having to specify step=1mrq2023-02-19 17:12:39 +0000
4f79b3724bFixed model setting not getting updated when TTS is unloaded, for when you change it and then load TTS (sorry for that brain worm)mrq2023-02-19 16:24:06 +0000
092dd7b2d7added more safeties and parameters to training yaml generator, I think I tested it extensively enoughmrq2023-02-19 16:16:44 +0000
f4e82fcf08I swear I committed forwarding arguments from the start scriptsmrq2023-02-19 15:01:16 +0000
3891870b5dUpdate notebook to follow the \'other\' way of installing mrq/tortoise-ttsmrq2023-02-19 07:22:22 +0000
d89b7d60e0forgot to divide checkpoint freq by iterations to get checkpoint countsmrq2023-02-19 07:05:11 +0000
485319c2bbdon't know what brain worms had me throw printing training output under verbosemrq2023-02-19 06:28:53 +0000
debdf6049aforgot to copy again from dev folder to git foldermrq2023-02-19 06:04:46 +0000
ae5d4023aafix for (I assume) some inconsistency with gradio sometimes-but-not-all-the-time coercing an empty Textbox into an empty string or sometimes None, but I also assume that might be a deserialization issue from JSON (cannot be assed to ask people to screenshot UI or send their ./config/generation.json for analysis, so get this hot monkeyshit patch)mrq2023-02-19 06:02:47 +0000
ec550d74fdchanged setup scripts to just clone mrq/tortoise-tts and install locally, instead of relying on pip's garbage git-integrationsmrq2023-02-19 05:29:01 +0000
57060190afabsolutely detest global semanticsmrq2023-02-19 05:12:09 +0000
f44239a85aadded polyfill for loading autoregressive models in case mrq/tortoise-tts absolutely refuses to updatemrq2023-02-19 05:10:08 +0000
e7d0cfaa82added some output parsing during training (print current iteration step, and checkpoint save), added option for verbose output (for debugging), added buffer size for output, full console output gets dumped on terminating trainingmrq2023-02-19 05:05:30 +0000
5fcdb19f8bI forgot to make it update the whisper model at runtimemrq2023-02-19 01:47:06 +0000
13d466baf5notebook tweaked, drive mounts and symlinks folders so I can stop having to wait a gorillion years to import voicesmrq2023-02-18 16:30:05 +0000
996e5217d2apparently anything after deactivate does not get ran, as it terminates the batch script.mrq2023-02-18 16:20:26 +0000
843bfbfb96Simplified generating training YAML, cleaned it up, training output is cleaned up and will "autoscroll" (only show the last 8 lines, refer to console for a full trace if needed)mrq2023-02-18 14:51:00 +0000
0dd5640a89forgot that call only worked if shell=Truemrq2023-02-18 14:14:42 +0000
2615cafd75added dropdown to select autoregressive model for TTS, fixed a bug where the settings saveer constantly fires I hate gradio so much why are dropdown.change broken to contiuously fire and send an empty arraymrq2023-02-18 14:10:26 +0000
c26bda4d96finally can get training to work under the web UImrq2023-02-18 03:36:08 +0000
809012c84ddebugging in colab is pure cock and ball torture because sometimes the files don't actually update when edited, and sometimes they update after I restart the runtime, notebook can't use venv because I can't source it in a subprocess shell callmrq2023-02-18 03:31:44 +0000
650eada8d5fix spawning training subprocess for unixesmrq2023-02-18 02:40:30 +0000
d5c1433268a bit of UI cleanup, import multiple audio files at once, actually shows progress when importing voices, hides audio metadata / latents if no generated settings are detected, preparing datasets shows its progress, saving a training YAML shows a message when done, training now works within the web UI, training output shows to web UI, provided notebook is cleaned up and uses a venv, etc.mrq2023-02-18 02:07:22 +0000
c75d0bc5dapulls DLAS for any updates since I might be actually updating it, added option to not load TTS on initialization to save VRAM when trainingmrq2023-02-17 20:43:12 +0000
mrq
mrq
lightmare