Been working on a universal tts finetuner for a bit so far works for 17 tts engines (xtts,coqui stuff, piper,etc), docker or cli

Little side project I’ve been doing outside of ebook2audiobook but anyway idk I guess it’s ready to share at this point Web GUI or CLI Has a docker cause yall like that So far the tts engines I’ve got supported are XTTS v2, XTTS v1, Piper TTS, VITS, MMS / Fairseq VITS, FastPitch, FastSpeech 2, Glow-TTS, DelightfulTTS, Tacotron2 DCA, Tacotron2 DDC, Tacotron2 Capacitron, Overflow, SpeedySpeech, FastSpeech, Align TTS, NeuralHMM-TTS You can even use ebook2audiobook to generate synthetic data of 1 voice cloning to then use to distill the voice in a (ittty bitty) piper model I’ll be making a video on it soon Hopefully this isn’t too niche ANYWAY wanted to see y’all’s thoughts on it enjoyyyyy