Skip to content

Releases: kan-bayashi/ParallelWaveGAN

Version 0.4.5

18 Aug 13:28
b66a877
Compare
Choose a tag to compare
  • Simplify decoding part
  • Add load_model function
  • Add inference method in each genearator
  • Add download_pretraiend_model function to download from google drive directly

Version 0.4.3

16 Aug 13:07
9a399c0
Compare
Choose a tag to compare

Version 0.4.2

15 Aug 09:22
a53f307
Compare
Choose a tag to compare
  • Fixed wrong loss naming
  • Fixed shuffle in distributed training
  • Fixed pad mode
  • Updated to be able to change PQMF paramters

Version 0.4.1

28 Jun 13:03
88a829b
Compare
Choose a tag to compare
  • Fix numba version issue
  • Support multi-key hdf5 scp format
  • Support npy scp format

Version 0.4.0

28 May 01:25
e40f046
Compare
Choose a tag to compare

What's new

  • Support Multi-band MelGAN
  • Support Full-band MelGAN

Version 0.3.5

11 May 08:31
bce614d
Compare
Choose a tag to compare

What's new

Scripts

Recipes

  • Add egs/libritts/voc1
  • Update structure #134
  • Add template recipe #141

Version 0.3.4

12 Mar 05:26
da60f08
Compare
Choose a tag to compare

What's new

Scripts

  • Support --pretrain option in training
  • Support --skip-wav-copy option in normalization
  • Support scp style input for all /bin scripts for ESPnet compatibility
  • Better parallelization (much faster in the case of the large dataset)

Recipes

  • Fix format: npy support
  • Add VCTK recipe
  • Add melgan.v3 config
  • Add parallel_wavegan.v3 config

Version 0.3.0

15 Feb 10:48
6861287
Compare
Choose a tag to compare

What's new

  • Support more recipes
  • Support new residual discriminator
  • Support MelGAN generator
  • Support MelGAN discriminator
  • And more refactoring...

Version 0.2.5

16 Nov 14:04
f07f2ef
Compare
Choose a tag to compare

Stable version release.