shaun 7d0ec62bf1 Update losses.py ... The block of code for use_l1_spec_loss is repeated which doubles the amount of L1 loss when enabled. The weight for L1 loss in hifigan_ljspeech configutation will likely need to be doubled to compensate (l1_spec_loss_weight)		2021-05-02 14:14:24 +02:00
..
__init__.py	rename the project to old TTS	2020-09-09 12:27:23 +02:00
hifigan.py	linter fixes	2021-04-12 13:14:11 +02:00
losses.py	Update losses.py	2021-05-02 14:14:24 +02:00
melgan.py	reformatting and styling	2021-04-12 11:47:39 +02:00
parallel_wavegan.py	reformatting and styling	2021-04-12 11:47:39 +02:00
pqmf.py	reformatting and styling	2021-04-12 11:47:39 +02:00
qmf.dat	rename the project to old TTS	2020-09-09 12:27:23 +02:00
upsample.py	reformatting and styling	2021-04-12 11:47:39 +02:00
wavegrad.py	reformatting and styling	2021-04-12 11:47:39 +02:00