modified logic to determine valid voice folders, also allows subdirs within the folder (for example: ./voices/SH/james/ will be named SH/james)

should fix #203

disable diarize button

a bunch of shit i had uncommited over the past while pertaining to VALL-E

fixes #185

added VALL-E inference support (very rudimentary, gimped, but it will load a model trained on a config generated through the web UI)

only include auto in the list of models under setting, nothing else

added mixing models (shamelessly inspired from voldy's web ui)

x_lim and y_lim for graph

actually make parsing VALL-E metrics work

do not write current whisper.json if there's no changes

Added option to unsqueeze sample batches after sampling

oops

DLAS is PIPified (but I'm still cloning it as a submodule to make updating it easier)

VALL-E config edits

forgot to not require it to be relative

option to set results folder location

cleanup, metrics are grabbed for vall-e trainer

fixed reload tts being broken due to being as untouched as I am

fixes

preparations for training an IPA-based finetune

added options to pick tokenizer json and diffusion model (so I don't have to add it in later when I get bored and add in diffusion training)

removed redundant training data (they exist within tortoise itself anyways), added utility: view tokenized text

fixes #131

fixes #132

fixes

:)

added mel LR weight (as I finally understand when to adjust the text), added text validation on dataset creation

blame https://git.ecker.tech/mrq/ai-voice-cloning/pulls/122

fixed last generation settings not actually load because brain worms

Disable loss ETA for now until I fix it

Merge branch 'master' into save_more_user_config

uh I don't remember, small things

updated several default configurations to not cause null/empty errors. also default samples/iterations to 16-30 ultra fast which is typically suggested.

Fixed Keep X Previous States

added option to trim silence using torchaudio's VAD

added fields to offset start/end slices to apply in bulk when slicing

rename transcribe button since it does more than transcribe

rely on the whisper.json for handling a lot more things

split slicing dataset routine so it can be done after the fact

added option to not slice audio when transcribing, added option to prepare validation dataset on audio duration, added a warning if youre using whisperx and you're slicing audio

master (#112)

rewrote how AIVC gets training metrics (need to clean up later)

forgot to fix reset settings to use the new arg-agnostic way

cleanup

expose options for CosineAnnealingLR_Restart (seems to be able to train very quickly due to the restarts

some cleanup

added loss graph, because I'm going to experiment with cosine annealing LR and I need to view my loss

forgot to save the simplified training input json first before touching any of the settings that dump to the yaml

forgot to update to finetune subdir