11 Commits

Author	SHA1	Message	Date
Edresson Casanova	72b2bac0f8	Load reference in 24khz to avoid issued with multiple sr references	2023-11-06 20:25:06 +01:00
Edresson Casanova	e45227d9ff	XTTS v2.0 (#3137) ... * Implement most similar ref training approach * Use non-enhanced hifigan for test samples * Add Perceiver * Update GPT Trainer for perceiver support * Update XTTS docs * Bug fix masking with XTTS perceiver * Bug fix on gpt forward * Bug Fix on XTTS v2.0 training * Add XTTS v2.0 unit tests * Add XTTS v2.0 inference unit tests * Bug Fix on diffusion inference * Add XTTS v2.0 training recipe * Placeholder model entry * Add cloning params to config * Make prompt embedding configurable * Make cloning configurable * Cheap fix for a cheaper fix * Prevent resampling * Update model entry * Update docs * Update requirements * Code linting * Add xtts v2 to sep tests * Bug fix on XTTS get_gpt_cond_latents * Bug fix on rebase * Make style * Bug fix in Japenese tokenizer * Add num2words to deps * Remove unused kwarg and added num_beams=1 as default --------- Co-authored-by: Eren G??lge <egolge@coqui.ai>	2023-11-06 14:58:18 +01:00
Edresson Casanova	ec7f54768a	Rebase bug fix and update recipe	2023-10-21 17:37:51 -03:00
Edresson Casanova	affaf11148	Add XTTS training unit test	2023-10-21 13:41:12 -03:00
Edresson Casanova	9e3598c3b7	Bug Fix on inference using XTTS trainer checkpoint	2023-10-21 13:37:21 -03:00
Edresson Casanova	c4ceaabe2c	Add test sentences during the training	2023-10-21 13:33:56 -03:00
Edresson Casanova	2f868dd5c2	Bug fix on reproducible evaluation	2023-10-21 13:33:56 -03:00
Edresson Casanova	bafab049c2	Add prompting masking	2023-10-21 13:33:56 -03:00
Edresson Casanova	47d613df3a	Add reproducible evaluation	2023-10-21 13:33:56 -03:00
Edresson Casanova	40a4e631ea	Update mel spectrogram for the style encoder	2023-10-21 13:33:56 -03:00
Edresson Casanova	a32961bcb4	Add XTTS base training code	2023-10-21 13:33:56 -03:00