Edresson Casanova 8d228ab22a Trick to Upsampling to High sampling rates using VITS model (#1456) ... * Add upsample VITS support * Fix the bug in inference * Fix lint checks * Add RMS based norm in save_wav method * Style fix * Add the period for VITS multi-period discriminator in model_args * Bug fix in speaker encoder load in inference time * Add unit tests * Remove useless detach_z_vocoder parameter * Add docs for VITS upsampling * Fix the docs * Rename TTS_part_sample_rate to encoder_sample_rate * Add upsampling_init and upsampling_z methods * Add asserts for encoder_sample_rate part * Move upsampling tests to test_vits.py		2022-04-26 11:47:46 +02:00
..
__init__.py	Update setup_model	2022-02-25 11:11:35 +01:00
align_tts.py	Update AlignTTS	2022-02-25 11:11:35 +01:00
base_tacotron.py	Update Tacotron models	2022-02-25 11:11:35 +01:00
base_tts.py	Add EmbeddingManager and BaseIDManager (#1374)	2022-03-31 13:41:16 +02:00
forward_tts.py	Fix import	2022-03-02 09:15:20 +01:00
glow_tts.py	Add EmbeddingManager and BaseIDManager (#1374)	2022-03-31 13:41:16 +02:00
tacotron.py	Update Tacotron models	2022-02-25 11:11:35 +01:00
tacotron2.py	Update Tacotron models	2022-02-25 11:11:35 +01:00
vits.py	Trick to Upsampling to High sampling rates using VITS model (#1456)	2022-04-26 11:47:46 +02:00