erogol
74e6e29479
add lr schedulers for generator and discriminator
2020-06-15 19:04:05 +02:00
erogol
1dfafe003d
fix multiband melgan inference
2020-06-15 19:04:05 +02:00
erogol
c866f23af6
remove weight norm for melgan generator
2020-06-15 19:04:05 +02:00
erogol
f9698af06e
correction for vocoder configs
2020-06-15 19:04:05 +02:00
erogol
0245a2e258
change alignment_score to alignment_error
2020-06-15 19:04:05 +02:00
erogol
9913724a70
TTS config update for using DDC
2020-06-15 19:04:05 +02:00
erogol
f0616a3b24
linter fix
2020-06-15 19:04:05 +02:00
erogol
55b8952c3d
run D in eval
2020-06-15 19:04:05 +02:00
erogol
78d43664a1
bug fix and var renaming
2020-06-15 19:04:05 +02:00
erogol
1daba4371d
bug fix vocoder model restore
2020-06-15 19:04:05 +02:00
erogol
b736c6cdac
bug fix for TTS model restore
2020-06-15 19:04:05 +02:00
erogol
d2cfab71d3
bug fix for DDC model eval run
2020-06-15 19:04:05 +02:00
erogol
2b377b5487
model config update
2020-06-15 19:04:05 +02:00
erogol
d7022a33b3
correct name
2020-06-15 19:04:05 +02:00
erogol
06d3eb42cb
bug fix for rwd discriminator
2020-06-15 19:04:05 +02:00
erogol
acb367be26
bug fix vocoder training
2020-06-15 19:04:05 +02:00
erogol
16eb15a5ff
lint updates
2020-06-15 19:04:05 +02:00
erogol
9f5f3910e4
check DDC parameters in config.json
2020-06-15 19:04:05 +02:00
erogol
01339e94a5
setup_model update following TacotronAbstract
2020-06-15 19:04:05 +02:00
erogol
4aaf57b50b
train.py update for DDC
2020-06-15 19:04:05 +02:00
erogol
fbf1689d18
update model tests for ddc
2020-06-15 19:04:05 +02:00
erogol
5962515581
update dummy model config
2020-06-15 19:04:05 +02:00
erogol
9559e3fc30
inherit TacotronAbstact with both tacotron and tacotron2
2020-06-15 19:04:05 +02:00
erogol
23f65df6c6
add DDC loss
2020-06-15 19:04:05 +02:00
erogol
cd93b7b351
update model config.json with double decoder consistency
2020-06-15 19:04:05 +02:00
erogol
ac24bdfddd
update README.md
2020-06-15 19:04:05 +02:00
erogol
aa06a0609d
tacotron abstract class
2020-06-15 19:04:05 +02:00
erogol
1b05bfce2e
visualization fix
2020-06-15 19:04:05 +02:00
erogol
8dc1d6a208
update README.md
2020-06-15 19:04:05 +02:00
erogol
6f4c1108f0
suppress pylint no-self-use for loss layers
2020-06-15 19:04:05 +02:00
erogol
6b1de26869
correct loss normalization and function refactoring
2020-06-15 19:04:05 +02:00
erogol
34eacb6383
reset loss weights
2020-06-15 19:04:05 +02:00
erogol
dfce9ab9b7
espeak install travis
2020-06-15 19:04:05 +02:00
erogol
d6b9a5738a
Ton of linter fixes
2020-06-15 19:04:05 +02:00
erogol
58117c0c6e
travis script for nose
2020-06-15 19:04:05 +02:00
erogol
502ba2d5c4
cardboard config update
2020-06-15 19:04:05 +02:00
erogol
b7b0c58e3f
update travis script
2020-06-15 19:04:05 +02:00
erogol
3a2e501b7a
bug fix
2020-06-15 19:04:05 +02:00
erogol
3dff81e7e2
multiscale subband stft loss and missing tb_logger for eval stats
2020-06-15 19:04:05 +02:00
erogol
d425daad5b
tb eval print
2020-06-15 19:04:05 +02:00
erogol
78cb7478d1
multiband rwd D config
2020-06-15 19:04:05 +02:00
erogol
604453bcb7
add multiband melgan config and rename loss weights for vocoder
2020-06-15 19:04:05 +02:00
erogol
1a49ce8956
bug fix
2020-06-15 19:04:05 +02:00
ForceCore
f675fca345
Fix phoneme cache file name aliasing problem
...
When the wav file has multiple dots in the file name,
_load_or_generate_phoneme_sequence would only use only the first segment
of the file name and cause overwrite of *_phoneme.npy
2020-06-15 19:04:05 +02:00
erogol
a361df3186
plot fix
2020-06-15 19:04:05 +02:00
erogol
0bb0ba182e
initial commit intro. to vocoder submodule
2020-06-15 19:02:18 +02:00
erogol
e9f3a476cf
use model_name prefix in tb_logger
2020-06-15 19:02:18 +02:00
erogol
a5fc2f578f
set state dict using direct state_dict dict
2020-06-15 19:02:18 +02:00
erogol
3034797211
differentiate modules on TB with a prefix
2020-06-15 19:02:18 +02:00
erogol
a2e74c58f9
add a non-existing value to avg values
2020-06-15 19:02:18 +02:00