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

..

aux_tests

Add EmbeddingManager and BaseIDManager (#1374)

2022-03-31 13:41:16 +02:00

bash_tests

remove bash running tests

2021-05-11 11:29:18 +02:00

data

Add Inference test using TTS API in all models unit tests

2022-02-18 21:06:08 +00:00

data_tests

Make style (#1405)

2022-03-16 12:13:55 +01:00

inference_tests

Update model file extension (#1422)

2022-03-22 17:55:00 +01:00

inputs

Update model file extension (#1422)

2022-03-22 17:55:00 +01:00

outputs

refactoring tests after Coqpit

2021-05-11 11:30:00 +02:00

text_tests

Make style and lint

2022-03-02 13:25:35 +01:00

tts_tests

Trick to Upsampling to High sampling rates using VITS model (#1456)

2022-04-26 11:47:46 +02:00

vocoder_tests

Update tests

2022-02-25 11:28:14 +01:00

zoo_tests

Add EmbeddingManager and BaseIDManager (#1374)

2022-03-31 13:41:16 +02:00

__init__.py

Add get_tests_data_path

2022-02-25 11:24:13 +01:00