gerazov
|
310d18325e
|
brushed up printing model load path and best loss path
|
2021-02-12 10:55:45 +01:00 |
gerazov
|
af46727517
|
loading last checkpoint/best_model works, deleting last best models options added, loading last best_loss added
|
2021-02-12 02:12:00 +01:00 |
Eren Gölge
|
a1e595790d
|
use default vocoders in server.pu
|
2021-02-11 15:31:39 +00:00 |
Eren Gölge
|
8aa6a0decb
|
set an output_sample_rate in synthesizer and use it for writing the wav
file
|
2021-02-11 15:28:07 +00:00 |
Eren Gölge
|
0c52d27d65
|
return the json entry of the downloaded model
|
2021-02-11 15:27:41 +00:00 |
Eren Gölge
|
1649ad3431
|
save_wav with a custom sampling rate
|
2021-02-11 15:27:20 +00:00 |
Eren Gölge
|
43f54d2dce
|
fix make_symbols
|
2021-02-11 15:26:52 +00:00 |
Eren Gölge
|
0657b38111
|
use default vocoder in synthesize.py
|
2021-02-11 15:26:17 +00:00 |
Eren Gölge
|
2043a9b5f5
|
define default vocoders
|
2021-02-11 15:25:55 +00:00 |
Eren Gölge
|
ff27690ca7
|
bug fix
|
2021-02-11 13:43:29 +00:00 |
Eren Gölge
|
bc131208be
|
fix spelling of a def argument and parse phonemes from config.json if
use_phonemes is True
|
2021-02-11 13:04:47 +00:00 |
Eren Gölge
|
f1799dbd60
|
docstring update
|
2021-02-11 11:25:31 +00:00 |
Eren Gölge
|
3baec4ea96
|
add missing phonemes to test_config.json
|
2021-02-11 11:14:39 +00:00 |
Eren Gölge
|
a3d1e65b34
|
Merge branch 'pr/adonispujols/646' into dev
|
2021-02-11 10:37:29 +00:00 |
Eren Gölge
|
3c2e13ca5c
|
fix the default vocoder name
|
2021-02-11 10:36:52 +00:00 |
Adonis Pujols
|
b29a7e9645
|
spelling error. should be multiband not mulitband
|
2021-02-11 04:49:28 -05:00 |
Adonis Pujols
|
6c824a6629
|
spelling error. should be multiband not mulitband
|
2021-02-11 04:48:53 -05:00 |
Eren Gölge
|
b08b8ca2a1
|
add russian phoneme char
|
2021-02-10 13:30:59 +00:00 |
Eren Gölge
|
9cad435288
|
css10 dataset preprocessor
|
2021-02-09 15:11:26 +00:00 |
Eren Gölge
|
cea5e517f2
|
download github model releases by model manager
|
2021-02-09 14:24:14 +00:00 |
Eren Gölge
|
c619859a3f
|
linter fixes
|
2021-02-09 11:43:17 +00:00 |
gerazov
|
e507373b55
|
final final fixes
|
2021-02-06 23:08:47 +01:00 |
gerazov
|
ad17dc9e76
|
final fixes
|
2021-02-06 23:05:01 +01:00 |
gerazov
|
8fdd08ea15
|
updated to current dev
|
2021-02-06 22:59:52 +01:00 |
gerazov
|
2705d27b28
|
changed train scripts
|
2021-02-06 22:29:30 +01:00 |
gerazov
|
4f8f274d6e
|
restructured arg parsing and processing to utils
|
2021-02-06 22:25:56 +01:00 |
Eren Gölge
|
e7e880f514
|
fix gdown
|
2021-02-05 13:42:24 +00:00 |
Eren Gölge
|
f4f6290eec
|
Merge branch 'pr/gerazov/641' into dev
|
2021-02-05 13:14:49 +00:00 |
Eren Gölge
|
d49757faaa
|
linter updates
|
2021-02-05 13:10:43 +00:00 |
Branislav Gerazov
|
f063545325
|
improve robustness of defining wavernn in config file
|
2021-02-05 13:26:33 +01:00 |
Branislav Gerazov
|
24ffa9e9f6
|
update wavernn test config, delete cap=True
|
2021-02-05 13:10:02 +01:00 |
Branislav Gerazov
|
cb77aef36c
|
waveRNN fix
|
2021-02-04 09:52:03 +01:00 |
Thorsten Mueller
|
d74866cb8e
|
Merge remote-tracking branch 'upstream/dev' into dev
Fix for circleci error mentioned in PR https://github.com/mozilla/TTS/pull/637
|
2021-02-02 19:40:18 +01:00 |
Thorsten Mueller
|
a82152eef3
|
Ups. Added missing ,
|
2021-02-02 19:29:16 +01:00 |
Thorsten Mueller
|
4cb4fcf02c
|
Set out_path to be required param.
|
2021-02-02 19:29:16 +01:00 |
Thorsten Mueller
|
c75ea74914
|
Added info if model already downloaded in --list_models
|
2021-02-02 19:29:16 +01:00 |
Eren Gölge
|
5c46543765
|
linter fixes and version updates for deps
|
2021-02-01 13:18:56 +00:00 |
Eren Gölge
|
8774e37444
|
unpin cython version and commentout pyworld in audio.py causing dep
issues
|
2021-02-01 11:34:05 +00:00 |
Eren Gölge
|
5beed0ddcd
|
Merge branch 'dev' of https://github.com/mozilla/TTS into dev
|
2021-02-01 11:27:14 +00:00 |
Eren Gölge
|
c7407571fa
|
fix #638
|
2021-02-01 10:05:55 +00:00 |
Eren Gölge
|
dfdac1def9
|
Merge pull request #636 from thorstenMueller/dev
Set out_path to be required param in compute_statistics.py.
|
2021-01-29 18:08:31 +01:00 |
Thorsten Mueller
|
44c4a49745
|
Set out_path to be required param.
|
2021-01-29 17:23:38 +01:00 |
Eren Gölge
|
536366dc0a
|
Merge pull request #635 from SanjaESC/patch-1
fix device mismatch wavegrad training
|
2021-01-29 16:42:25 +01:00 |
Eren Gölge
|
0354b6f35e
|
move hubconf
|
2021-01-29 15:28:32 +00:00 |
Eren Gölge
|
aa5f24608a
|
hubconf.py and load .models.json from the defualt location by mange.py
|
2021-01-29 15:28:26 +00:00 |
Alexander Korolev
|
e81ebec7a8
|
fix device mismatch wavegrad training
this should fixe the device mismatch as seen here https://github.com/mozilla/TTS/issues/622#issue-789802916
|
2021-01-29 15:18:59 +01:00 |
Eren Gölge
|
a926aa106d
|
reorder imports
|
2021-01-29 01:36:21 +01:00 |
Eren Gölge
|
8a6eee7fec
|
distill import statement, check python version in setup.py
|
2021-01-28 17:04:08 +01:00 |
Eren Gölge
|
131a163c95
|
Merge pull request #628 from thorstenMueller/dev
Added info if model already downloaded in --list_models
|
2021-01-28 13:10:06 +01:00 |
Alexander Korolev
|
ca28e05ed7
|
update fixed stopnet_pos_weight parameter
config parameter c.stopnet_pos_weight has currently no effect as it is not used.
|
2021-01-27 16:33:25 +01:00 |