erogol
|
71c382be14
|
copy model scale stats file with config.json to the trianing folder, fixed for model inits
|
2021-01-06 13:19:40 +01:00 |
|
erogol
|
aa40fe1aa0
|
SS model refacotring for multi speaker
|
2021-01-06 13:19:40 +01:00 |
|
erogol
|
eb555855e4
|
small fixes
|
2021-01-06 13:19:40 +01:00 |
|
erogol
|
5901a00576
|
argument rename
|
2021-01-06 13:19:40 +01:00 |
|
erogol
|
4ef083f0f1
|
select decoder type for SS
|
2021-01-06 13:19:40 +01:00 |
|
erogol
|
d5a0190c4b
|
update copy_config_file to copy_model_files
|
2021-01-06 13:19:40 +01:00 |
|
erogol
|
8971c59b2d
|
plot eval alignment score right
|
2021-01-06 13:19:40 +01:00 |
|
erogol
|
3fa408a5ea
|
change order BN + ReLU to ReLU + BN for SS
|
2021-01-06 13:19:40 +01:00 |
|
erogol
|
ac5c9217d1
|
positional encoding masking for SS
|
2021-01-06 13:19:40 +01:00 |
|
erogol
|
7c95b11fe8
|
add test data for attention masking in SS
|
2021-01-06 13:19:40 +01:00 |
|
erogol
|
fede46e96e
|
pylint and test fixes
|
2021-01-06 13:19:40 +01:00 |
|
erogol
|
2abe3df153
|
compute_attention_masks.py
|
2021-01-06 13:19:40 +01:00 |
|
erogol
|
cf869e8922
|
add SS files
|
2021-01-06 13:19:40 +01:00 |
|
erogol
|
4b1065f6db
|
test script for speedy_speech training
|
2021-01-06 13:19:40 +01:00 |
|
erogol
|
61b72e6438
|
remove travis config
|
2021-01-06 13:19:40 +01:00 |
|
erogol
|
e4680e1b99
|
plot float16 alignments
|
2021-01-06 13:19:40 +01:00 |
|
erogol
|
13c6665c92
|
inference for SS
|
2021-01-06 13:19:40 +01:00 |
|
erogol
|
30788960a8
|
check SS model parameters
|
2021-01-06 13:19:40 +01:00 |
|
erogol
|
5cae2c5742
|
make optional position encoding for speedyspeech
|
2021-01-06 13:19:40 +01:00 |
|
erogol
|
dc4a16d62e
|
speedy speehc losses
|
2021-01-06 13:19:40 +01:00 |
|
erogol
|
d62cac7252
|
fix glow-tts prenet bug fix
|
2021-01-06 13:19:40 +01:00 |
|
erogol
|
a1d5a9ddda
|
config update tyo use noise for augmentation
|
2021-01-06 13:19:40 +01:00 |
|
erogol
|
96cf247934
|
update readme
|
2021-01-06 13:19:40 +01:00 |
|
erogol
|
022af74d74
|
update prompt msg
|
2021-01-06 13:19:40 +01:00 |
|
erogol
|
57ef53bef3
|
update argumnet check for non tacotron models
|
2021-01-06 13:19:40 +01:00 |
|
erogol
|
27a75de15f
|
update processors for loading attention maps
|
2021-01-06 13:19:40 +01:00 |
|
erogol
|
fa6907fa0e
|
update glow-tts parameters and fix rel-attn-win size
|
2021-01-06 13:19:40 +01:00 |
|
erogol
|
7b20d8cbd3
|
implement residual BN convolution and add it as an alternative encoder for glow-tts. also generic layers to layers/generic
|
2021-01-06 13:19:40 +01:00 |
|
erogol
|
973754d893
|
fix for init glow-tts
|
2021-01-06 13:19:40 +01:00 |
|
erogol
|
f81af4eb0d
|
config update disable guided attention for dynamic conv attention
|
2021-01-06 13:19:40 +01:00 |
|
erogol
|
29b17c0808
|
bug fix for gradual training
|
2021-01-06 13:19:40 +01:00 |
|
erogol
|
5c50e104d6
|
config update
|
2021-01-06 13:19:40 +01:00 |
|
erogol
|
6478d552dc
|
tacotron training bug fix
|
2021-01-06 13:19:40 +01:00 |
|
erogol
|
1dd086577a
|
tacotron training bug fix
|
2021-01-06 13:18:41 +01:00 |
|
erogol
|
fa20638083
|
config for ljspeech dynamic conv attention
|
2021-01-06 13:18:41 +01:00 |
|
erogol
|
070146e143
|
add monotonic dynamic convolution attention
|
2021-01-06 13:18:41 +01:00 |
|
erogol
|
18392bc13a
|
Merge branch 'dev' of https://github.com/mozilla/TTS into dev
|
2021-01-06 13:18:08 +01:00 |
|
Eren Gölge
|
4cfde34ad8
|
Merge pull request #602 from thorstenMueller/dev
Increase robustness in synthesize with wavegrad model
|
2020-12-21 09:51:03 +01:00 |
|
Thorsten Mueller
|
f673f8f74d
|
Added support for npy output from tune-wavegrad
|
2020-12-19 22:51:22 +01:00 |
|
Thorsten Mueller
|
2aa0354b44
|
Fix for 'NoneType' object has no attribute 'to'
|
2020-12-19 22:37:03 +01:00 |
|
Thorsten Mueller
|
28a64221ea
|
Improve robostness on cpu / gpu model mix
|
2020-12-19 22:23:28 +01:00 |
|
Thorsten Müller
|
8c81ca7bfd
|
Merge pull request #1 from mozilla/dev
Sync with Mozilla TTS dev branch
|
2020-12-19 22:10:46 +01:00 |
|
erogol
|
9cf474ac3d
|
add CODE_OWNERS.rst
|
2020-12-17 16:44:50 +01:00 |
|
erogol
|
2df0e022d0
|
Add CODE_OWNERS and GOVERNANCE
|
2020-12-17 14:45:58 +01:00 |
|
erogol
|
8293751a38
|
remove mozilla from server page
|
2020-12-17 12:28:28 +01:00 |
|
erogol
|
df4b7f2166
|
remove mozilla from readme
|
2020-12-16 04:25:57 +01:00 |
|
erogol
|
639fa29261
|
update speaker id casting for glow-tts
|
2020-12-14 16:58:47 +01:00 |
|
erogol
|
999120ecdf
|
Merge branch 'dev' of https://github.com/mozilla/TTS into dev
|
2020-12-12 18:50:14 +01:00 |
|
Eren Gölge
|
f0f652e122
|
Merge pull request #597 from Mic92/negative
inflect negative numbers correctly
|
2020-12-12 18:50:03 +01:00 |
|
erogol
|
f611e6ac01
|
Merge branch 'dev' of https://github.com/mozilla/TTS into dev
|
2020-12-12 18:47:59 +01:00 |
|