10 Commits

Author	SHA1	Message	Date
Edresson Casanova	569decba64	Add Pitch Predictor conditioned on enc	2022-06-17 17:39:17 -03:00
Eren Gölge	f70e82cd19	Use fsspec and torch for embedding file IO (#1581) ... * Use fsspec and torch for embedding file * Fixup * Fix load and save files * Fix compute embedding script * Set use_cuda to true if available * Add dummy speakers.pth file * Make style * Change default speakers file extension Co-authored-by: WeberJulian <julian.weber@hotmail.fr>	2022-06-01 13:49:42 +02:00
Edresson Casanova	fc7081fc5e	Add Inference test using TTS API in all models unit tests	2022-02-18 21:06:08 +00:00
Eren Gölge	419735f440	refactor and fix multi-speaker training in Trainer and Tacotron models	2021-06-28 17:03:19 +02:00
Eren Gölge	877bf66b61	reduce size of the metadata.csv used at testing	2021-06-28 17:03:19 +02:00
Eren Gölge	f5a9950a2e	phoneme files for testing	2021-05-19 03:16:57 +02:00
Eren Gölge	32e6afc009	add `SpeakerManager` tests	2021-04-23 18:04:37 +02:00
erogol	7c95b11fe8	add test data for attention masking in SS	2021-01-06 13:19:40 +01:00
erogol	6948e4ce38	change sample data	2020-06-16 12:35:28 +02:00
Eren Golge	25c07e3d85	add a subset of ljspeech for testing	2019-07-19 12:06:46 +02:00